Scene-level point cloud registration is very challenging when considering dynamic foregrounds. Existing indoor datasets mostly assume rigid motions, so the trained models cannot robustly handle scenes with non-rigid motions. On the other hand, non-rigid datasets are mainly object-level, so the trained models cannot generalize well to complex scenes. This paper presents HybridReg, a new approach to 3D point cloud registration, learning uncertainty mask to account for hybrid motions: rigid for backgrounds and non-rigid/rigid for instance-level foregrounds. First, we build a scene-level 3D registration dataset, namely HybridMatch, designed specifically with strategies to arrange diverse deforming foregrounds in a controllable manner. Second, we account for different motion types and formulate a mask-learning module to alleviate the interference of deforming outliers. Third, we exploit a simple yet effective negative log-likelihood loss to adopt uncertainty to guide the feature extraction and correlation computation. To our best knowledge, HybridReg is the first work that exploits hybrid motions for robust point cloud registration. Extensive experiments show HybridReg's strengths, leading it to achieve state-of-the-art performance on both widely-used indoor and outdoor datasets.

Controversial contents largely inundate the Internet, infringing various cultural norms and child protection standards. Traditional Image Content Moderation (ICM) models fall short in producing precise moderation decisions for diverse standards, while recent multimodal large language models (MLLMs), when adopted to general rule-based ICM, often produce classification and explanation results that are inconsistent with human moderators. Aiming at flexible, explainable, and accurate ICM, we design a novel rule-based dataset generation pipeline, decomposing concise human-defined rules and leveraging well-designed multi-stage prompts to enrich short explicit image annotations. Our ICM-Instruct dataset includes detailed moderation explanation and moderation Q-A pairs. Built upon it, we create our ICM-Assistant model in the framework of rule-based ICM, making it readily applicable in real practice. Our ICM-Assistant model demonstrates exceptional performance and flexibility. Specifically, it significantly outperforms existing approaches on various sources, improving both the moderation classification (36.8% on average) and moderation explanation quality (26.6% on average) consistently over existing MLLMs. Caution: Content includes offensive language or images.

Estimating the 3D pose of hand and potential hand-held object from monocular images is a longstanding challenge. Yet, existing methods are specialized, focusing on either bare-hand or hand interacting with object. No method can flexibly handle both scenarios and their performance degrades when applied to the other scenario. In this paper, we propose UniHOPE, a unified approach for general 3D hand-object pose estimation, flexibly adapting both scenarios. Technically, we design a grasp-aware feature fusion module to integrate hand-object features with an object switcher to dynamically control the hand-object pose estimation according to grasping status. Further, to uplift the robustness of hand pose estimation regardless of object presence, we generate realistic de-occluded image pairs to train the model to learn object-induced hand occlusions, and formulate multi-level feature enhancement techniques for learning occlusion-invariant features. Extensive experiments on three commonly-used benchmarks demonstrate UniHOPE’s SOTA performance in addressing hand-only and hand-object scenarios. Code will be released on https://github.com/JoyboyWang/UniHOPE_Pytorch.

Shadows are often under-considered or even ignored in image editing applications, limiting the realism of the edited results. In this paper, we introduce MetaShadow, a three-in-one versatile framework that enables detection, removal, and controllable synthesis of shadows in natural images in an object-centered fashion. MetaShadow combines the strengths of two cooperative components: Shadow Analyzer, for object-centered shadow detection and removal, and Shadow Synthesizer, for reference-based controllable shadow synthesis. Notably, we optimize the learning of the intermediate features from Shadow Analyzer to guide Shadow Synthesizer to generate more realistic shadows that blend seamlessly with the scene. Extensive evaluations on multiple shadow benchmark datasets show significant improvements of MetaShadow over the existing state-of-the-art methods on object-centered shadow detection, removal, and synthesis. MetaShadow excels in image-editing tasks such as object removal, relocation, and insertion, pushing the boundaries of object-centered image editing.

Traffic Anomaly Understanding (TAU) is essential for improving public safety and transportation efficiency by enabling timely detection and response to incidents. Beyond existing methods, which rely largely on visual data, we propose to consider audio cues, a valuable source that offers strong hints to anomaly scenarios such as crashes and honking. Our contributions are twofold. First, we compile AV-TAU, the first large-scale audio-visual dataset for TAU, providing 29,865 traffic anomaly videos and 149,325 Q&A pairs, while supporting five essential TAU tasks. Second, we develop EchoTraffic, a multimodal LLM that integrates audio and visual data for TAU, through our audio-insight frame selector and dynamic connector to effectively extract crucial audio cues for anomaly understanding with a two-phase training framework. Experimental results on AV-TAU manifest that EchoTraffic sets a new SOTA performance in TAU, outperforming the existing multimodal LLMs. Our contributions, including AV-TAU and EchoTraffic, pave a new direction for multimodal TAU.

Lifting multi-view 2D instance segmentation to a radiance field has proven effective to enhance 3D understanding. Existing works rely on direct matching for end-to-end lifting, yielding inferior results, or employ a two-stage solution constrained by complex preor post-processing. In this work, we design Unified-Lift, a new end-to-end object-aware lifting approach that aims for high-quality 3D segmentation based on our object-aware 3D Gaussian representation. To start, we augment each Gaussian point with a Gaussian-level feature learned using a contrastive loss to encode instance information. Importantly, we introduce a learnable object-level codebook to account for individual objects in the scene for an explicit object-level understanding and associate the encoded object-level features with the Gaussian-level point features for segmentation predictions. While promising, achieving effective codebook learning is nontrivial and a naive solution leads to degraded performance. Hence, we formulate the association learning module and the noisy label filtering module for effective and robust codebook learning. We conduct experiments on three benchmarks LERF-Masked, Replica, and Messy Rooms. Both qualitative and quantitative results manifest that our Unified-Lift clearly outperforms existing methods in terms of segmentation quality and time efficiency.

Learning generative models of 3D point clouds is one of the fundamental problems in 3D generative learning. One of the key properties of point clouds is their permutation invariance, i.e., changing the order of points in a point cloud does not change the shape they represent. In this paper, we analyze the recently proposed equivariant OT flows that learn permutation invariant generative models for point-based molecular data and we show that these models scale poorly on large point clouds. Also, we observe learning (equivariant) OT flows is generally challenging since straightening flow trajectories makes the learned flow model complex at the beginning of the trajectory. To remedy these, we propose not-so-optimal transport flow models that obtain an approximate OT by an offline OT precomputation, enabling an efficient construction of OT pairs for training. During training, we can additionally construct a hybrid coupling by combining our approximate OT and independent coupling to make the target flow models easier to learn. In an extensive empirical study, we show that our proposed model outperforms prior diffusion- and flow -based approaches on a wide range of unconditional generation and shape completion on the ShapeNet benchmark.

We present PanoGPS, a new approach for generating indoor panoramas, capable of following a room layout sketch and description text to generate panoramas with geometrically-plausible room layouts and semantically-consistent contents. Overall, our idea is to inform the generative model collectively with the two inputs, to inspire it to implicitly generate and refine a unified latent code for panorama generation. Specifically, we first propose using the semantic layout map to encode the room geometry to condition the generative model with plausible geometric information. Second, we establish a pipeline to integrate features from the two inputs and generate a single unified latent code that describes both the room layout and room contents of the target panorama. Third, we progressively refine the latent code to produce a coarse panorama to enforce seamless left-right border connections, while iteratively upsizing the coarse panorama with details. Our method outperforms existing approaches by generating high-quality panoramas with geometrically plausible structures and semantically meaningful content. Code is available at: https://github.com/wumengyangok/PanoGPS

Observing that the key for robotic action planning is to understand the target-object motion when its associated part is manipulated by the end effector, we propose to generate the 3D object-part scene flow and extract its transformations to solve the action trajectories for diverse embodiments. The advantage of our approach is that it derives the robot action explicitly from object motion prediction, yielding a more robust policy by understanding the object motions. Also, beyond policies trained on embodiment-centric data, our method is embodiment-agnostic, generalizable across diverse embodiments, and being able to learn from human demonstrations. Our method comprises three components: an object-part predictor to locate the part for the end effector to manipulate, an RGBD video generator to predict future RGBD videos, and a trajectory planner to extract embodiment-agnostic transformation sequences and solve the trajectory for diverse embodiments. Trained on videos even without trajectory data, our method still outperforms existing works significantly by 27.7% and 26.2% on the prevailing virtual environments MetaWorld and Franka-Kitchen, respectively. Furthermore, we conducted real-world experiments, showing that our policy, trained only with human demonstration, can be deployed to various embodiments.

Generalized policy and execution efficiency constitute the two critical challenges in robotic manipulation. While recent foundation policies benefit from the common-sense reasoning capabilities of internet-scale pretrained vision-language models (VLMs), they often suffer from low execution frequency. To mitigate this dilemma, dual-system approaches have been proposed to leverage a VLM-based System 2 module for handling high-level decision-making, and a separate System 1 action module for ensuring real-time control. However, existing designs maintain both systems as separate models, limiting System 1 from fully leveraging the rich pretrained knowledge from the VLM-based System 2. In this work, we propose Fast-in-Slow (FiS), a unified dual-system vision-language-action (VLA) model that embeds the System 1 execution module within the VLM-based System 2 by partially sharing parameters. This innovative paradigm not only enables high-frequency execution in System 1, but also facilitates coordination between multimodal reasoning and execution components within a single foundation model of System 2. Given their fundamentally distinct roles within FiS-VLA, we design the two systems to incorporate heterogeneous modality inputs alongside asynchronous operating frequencies, enabling both fast and precise manipulation. To enable coordination between the two systems, a dual-aware co-training strategy is proposed that equips System 1 with action generation capabilities while preserving System 2’s contextual understanding to provide stable latent conditions for System 1. For evaluation, FiS-VLA outperforms previous state-of-the-art methods by 8% in simulation and 11% in real-world tasks in terms of average success rate, while achieving a 117.7 Hz control frequency with action chunk set to eight. Project web page: https://fast-in-slow.github.io.

Open-vocabulary 3D segmentation is a fundamental yet challenging task, requiring a mutual understanding of both segmentation and language. However, existing Gaussian-splatting-based methods rely either on a single 3D language field, leading to inferior segmentation, or on pre-computed class-agnostic segmentations, suffering from error accumulation. To address these limitations, we present COS3D, a new collaborative prompt-segmentation framework that contributes to effectively integrating complementary language and segmentation cues throughout its entire pipeline. We first introduce the new concept of collaborative field, comprising an instance field and a language field, as the cornerstone for collaboration. During training, to effectively construct the collaborative field, our key idea is to capture the intrinsic relationship between the instance field and language field, through a novel instance-to-language feature mapping and designing an efficient two-stage training strategy. During inference, to bridge distinct characteristics of the two fields, we further design an adaptive language-to-instance prompt refinement, promoting high-quality prompt-segmentation inference. Extensive experiments not only demonstrate COS3D's leading performance over existing methods on two widely-used benchmarks but also show its high potential to various applications,~\ie, novel image-based 3D segmentation, hierarchical segmentation, and robotics.

A K-hedral tiling of a 2D finite domain is a covering of the domain with tiles without gaps or overlaps, where each tile is congruent to one of the K distinct shapes called prototiles. K, the number of prototiles, is preferred to be as small as possible for congruent tiling appearance and reducing fabrication cost, e.g., by molding. Typically, a forward approach is adopted to produce K-hedral tilings by prescribing a set of prototiles and placing prototile instances (i.e., tiles) to cover the input domain. However, the prescribed prototile set may not be sufficient to tile the domain (for small K) or may lead to tiling results with excessive prototiles more than needed (for large K).

This paper presents a new approach to estimate accurate and robust 3D semantic correspondence with the hierarchical neural semantic representation. Our work has three key contributions. First, we design the hierarchical neural semantic representation (HNSR), which consists of a global semantic feature to capture high-level structure and multi-resolution local geometric features to preserve fine details, by carefully harnessing 3D priors from pre-trained 3D generative models. Second, we design a progressive global-to-local matching strategy, which establishes coarse semantic correspondence using the global semantic feature, then iteratively refines it with local geometric features, yielding accurate and semantically-consistent mappings. Third, our framework is training-free and broadly compatible with various pre-trained 3D generative backbones, demonstrating strong generalization across diverse shape categories. Our method also supports various applications, such as shape co-segmentation, keypoint matching, and texture transfer, and generalizes well to structurally diverse shapes, with promising results even in cross-category scenarios. Both qualitative and quantitative evaluations show that our method outperforms previous state-of-the-art techniques.

Robustly reconstructing 3D hand mesh from a single image is very challenging, due to (i) the lack of diversity in existing real-world datasets and (ii) the ambiguity in occluded hand regions. While data synthesis helps relieve issue (i), the syn-to-real gap still hinders its usage. For issue (ii), most previous works produce deterministic results while other probabilistic methods rely on ground truths to choose the best hypothesis. In this work, we explore the diffusion model to alleviate these problems by collectively considering two perspectives: (i) conditional synthesis and sampling approach for realistic data generation and (ii) probabilistic modeling with progressive multi-hypothesis aggregation. First, we present HandBooster, a new approach to uplift the data diversity by training a conditional generative space on hand-object interactions and sampling the space to synthesize effective data with reliable 3D annotations and diverse hand appearances, poses, views, and backgrounds. Second, we design HandBooster+, a probabilistic diffusion-based model to further boost the 3D hand-mesh reconstruction performance by progressively aggregating the multiple hypotheses. Extensive experimental results show that our method significantly improves several baselines and achieves SOTA on the HO3D and DexYCB benchmarks.

This paper presents LEGO ® -Maker, a new learning-based generative model that can effectively consider over 100 unique brick types and rapidly generate hundreds of bricks to create LEGO ® models conditioned on images. This work has three major technical contributions that enable it to achieve surpassing capabilities beyond existing generative approaches. First, we design a compact LEGO ® tokenization scheme to serialize LEGO ® models and bricks into tokens for autoregressive learning. Second, we build LEGO ® -Maker, an autoregressive image-conditioned architecture, with a multi-token prediction strategy to encourage pre-considering multiple brick attributes and a rollback mechanism for collision-free generation. Third, we propose an effective data preparation pipeline with a procedural generator to synthesize LEGO ® models and a LEGO ® -to-real image translator distilled from a large vision language model to translate LEGO ® renderings into associated photorealistic images, leveraging rich prior to address the scarcity of image-to-LEGO ® data. Extensive evaluations and comparisons are conducted on two object categories, facade and portrait, over metrics in four aspects: geometry, color, semantics, and structural integrity, together with a user study. Experimental results demonstrate the versatility and compelling strengths of LEGO ® -Maker in producing structures and details given by the reference image. Also, the evaluation scores manifest that our method clearly surpasses the baselines, consistently for all evaluation metrics.

Hand shadow art is a captivating art form, creatively using hand shadows to reproduce expressive shapes on the wall. In this work, we study an inverse problem: given a target shape, find the poses of left and right hands that together best produce a shadow resembling the input. This problem is nontrivial, since the design space of 3D hand poses is huge while being restrictive due to anatomical constraints. Also, we need to attend to the input's shape and crucial features, though the input is colorless and textureless. To meet these challenges, we design Hand-Shadow Poser, a three-stage pipeline, to decouple the anatomical constraints (by hand) and semantic constraints (by shadow shape): (i) a generative hand assignment module to explore diverse but reasonable left/right-hand shape hypotheses; (ii) a generalized hand-shadow alignment module to infer coarse hand poses with a similarity-driven strategy for selecting hypotheses; and (iii) a shadow-feature-aware refinement module to optimize the hand poses for physical plausibility and shadow feature preservation. Further, we design our pipeline to be trainable on generic public hand data, thus avoiding the need for any specialized training dataset. For method validation, we build a benchmark of 210 diverse shadow shapes of varying complexity and a comprehensive set of metrics, including a novel DINOv2-based evaluation metric. Through extensive comparisons with multiple baselines and user studies, our approach is demonstrated to effectively generate bimanual hand poses for a large variety of hand shapes for over 85% of the benchmark cases.

We present a novel visualization-driven illumination model for density plots, a new technique to enhance density plots by effectively revealing the detailed structures in high- and medium-density regions and outliers in low-density regions, while avoiding artifacts in the density field's colors. When visualizing large and dense discrete point samples, scatterplots and dot density maps often suffer from overplotting, and density plots are commonly employed to provide aggregated views while revealing underlying structures. Yet, in such density plots, existing illumination models may produce color distortion and hide details in low-density regions, making it challenging to look up density values, compare them, and find outliers. The key novelty in this work includes (i) a visualization-driven illumination model that inherently supports density-plot-specific analysis tasks and (ii) a new image composition technique to reduce the interference between the image shading and the color-encoded density values. To demonstrate the effectiveness of our technique, we conducted a quantitative study, an empirical evaluation of our technique in a controlled study, and two case studies, exploring twelve datasets with up to two million data point samples.

Estimating 3D hand mesh from RGB images is a longstanding track, in which occlusion is one of the most challenging problems. Existing attempts towards this task often fail when the occlusion dominates the image space. In this paper, we propose SiMA-Hand, aiming to boost the mesh reconstruction performance by Single-to-Multi-view Adaptation. First, we design a multi-view hand reconstructor to fuse information across multiple views by holistically adopting feature fusion at image, joint, and vertex levels. Then, we introduce a single-view hand reconstructor equipped with SiMA. Though taking only one view as input at inference, the shape and orientation features in the single-view reconstructor can be enriched by learning non-occluded knowledge from the extra views at training, enhancing the reconstruction precision on the occluded regions. We conduct experiments on the Dex-YCB and HanCo benchmarks with challenging object- and self-caused occlusion cases, manifesting that SiMA-Hand consistently achieves superior performance over the state of the arts. Code will be released on https://github.com/JoyboyWang/SiMA-Hand Pytorch.

Reconstructing 3D hand mesh robustly from a single image is very challenging, due to the lack of diversity in existing real-world datasets. While data synthesis helps relieve the issue, the syn-to-real gap still hinders its usage. In this work, we present HandBooster, a new approach to uplift the data diversity and boost the 3D hand-mesh reconstruction performance by training a conditional generative space on hand-object interactions and purposely sampling the space to synthesize effective data samples. First, we construct versatile content-aware conditions to guide a diffusion model to produce realistic images with diverse hand appearances, poses, views, and backgrounds; favorably, accurate 3D an-notations are obtained for free. Then, we design a novel condition creator based on our similarity-aware distribution sampling strategies to deliberately find novel and realistic interaction poses that are distinctive from the training set. Equipped with our method, several baselines can be significantly improved beyond the SOTA on the HO3D and DexYCB benchmarks. Our code will be released on https://github.com/hxwork/HandBooster_Pytorch.

The progression in large-scale 3D generative models has been impeded by significant resource requirements for training and challenges like inefficient representations. This paper introduces Make-A-Shape, a novel 3D generative model trained on a vast scale, using 10 million publicly-available shapes. We first innovate the wavelet-tree representation to encode high-resolution SDF shapes with minimal loss, leveraging our newly-proposed subband coefficient filtering scheme. We then design a subband coefficient packing scheme to facilitate diffusion-based generation and a subband adaptive training strategy for effective training on the large-scale dataset. Our generative framework is versatile, capable of conditioning on various input modalities such as images, point clouds, and voxels, enabling a variety of downstream applications, e.g., unconditional generation, completion, and conditional generation. Our approach clearly surpasses the existing baselines in delivering high-quality results and can efficiently generate shapes within two seconds for most conditions.

We introduce camera ray matching (CRAYM) into the joint optimization of camera poses and neural fields from multi-view images. The optimized field, referred to as a feature volume, can be “probed” by the camera rays for novel view synthesis (NVS) and 3D geometry reconstruction. One key reason for matching camera rays, instead of pixels as in prior works, is that the camera rays can be parameterized by the feature volume to carry both geometric and photometric information. Multi-view consistencies involving the camera rays and scene rendering can be naturally integrated into the joint optimization and network training, to impose physically meaningful constraints to improve the final quality of both the geometric reconstruction and photorealistic rendering. We formulate our per-ray optimization and matched ray coherence by focusing on camera rays passing through keypoints in the input images to elevate both the efficiency and accuracy of scene correspondences. Accumulated ray features along the feature volume provide a means to discount the coherence constraint amid erroneous ray matching. We demonstrate the effectiveness of CRAYM for both NVS and geometry reconstruction, over dense- or sparse-view settings, with qualitative and quantitative comparisons to state-of-the-art alternatives.

Reconstructing 3D geometry from unoriented point clouds can benefit many downstream tasks. Recent shape modeling methods mostly adopt implicit neural representation to fit a signed distance field (SDF) and optimize the network by unsigned supervision. However, these methods occasionally have difficulty in finding the coarse shape for complicated objects, especially suffering from the "ghost" surfaces (i.e., fake surfaces that should not exist). To guide the network quickly fit the coarse shape, we propose to utilize the signed supervision in regions that are obviously outside the object and can be easily determined, resulting in our semi-signed supervision. To better recover high-fidelity details, a novel loss-based region sampling strategy and a progressive positional encoding (PE) method are applied to prioritize the optimization towards underfitting and complicated regions. Specifically, we voxelize and partition the object space into sign-known and sign-uncertain regions, in which different supervisions are applied. Besides, we adaptively adjust the sampling rate of each voxel according to the tracked reconstruction loss, so that the network can focus more on the complicated under-fitting regions. We conduct extensive experiments to demonstrate that our method achieves state-of-the-art performance compared to the existing fitting-based methods and comparable performance to learning-based methods on multiple datasets. The code is publicly available at https://github.com/Runsong123/SSP.

Instance shadow detection, crucial for applications such as photo editing and light direction estimation, has undergone significant advancements in predicting shadow instances, object instances, and their associations. The extension of this task to videos presents challenges in annotating diverse video data and addressing complexities arising from occlusion and temporary disappearances within associations. In response to these challenges, we introduce ViShadow, a semi-supervised video instance shadow detection framework that leverages both labeled image data and unlabeled video data for training. ViShadow features a two-stage training pipeline: the first stage, utilizing labeled image data, identifies shadow and object instances through contrastive learning for cross-frame pairing. The second stage employs unlabeled videos, incorporating an associated cycle consistency loss to enhance tracking ability. A retrieval mechanism is introduced to manage temporary disappearances, ensuring tracking continuity. The SOBA-VID dataset, comprising unlabeled training videos and labeled testing videos, along with the SOAP-VID metric, is introduced for the quantitative evaluation of VISD solutions. The effectiveness of ViShadow is further demonstrated through various video-level applications such as video inpainting, instance cloning, shadow editing, and text-instructed shadow-object manipulation.

This paper presents a computational pipeline for creating personalized, physical LEGO ®1 figurines from user-input portrait photos. The generated figurine is an assembly of coherently-connected LEGO ® bricks detailed with uv-printed decals, capturing prominent features such as hairstyle, clothing style, and garment color, and also intricate details such as logos, text, and patterns. This task is non-trivial, due to the substantial domain gap between unconstrained user photos and the stylistically-consistent LEGO ® figurine models. To ensure assemble-ability by LEGO ® bricks while capturing prominent features and intricate details, we design a three-stage pipeline: (i) we formulate a CLIP-guided retrieval approach to connect the domains of user photos and LEGO ® figurines, then output physically-assemble-able LEGO ® figurines with decals excluded; (ii) we then synthesize decals on the figurines via a symmetric U-Nets architecture conditioned on appearance features extracted from user photos; and (iii) we next reproject and uv-print the decals on associated LEGO ® bricks for physical model production. We evaluate the effectiveness of our method against eight hundred expert-designed figurines, using a comprehensive set of metrics, which include a novel GPT-4V-based evaluation metric, demonstrating superior performance of our method in visual quality and resemblance to input photos. Also, we show our method's robustness by generating LEGO ® figurines from diverse inputs and physically fabricating and assembling several of them.

This paper presents the first learning-based generative pipeline for effectively creating 3D LEGO® 1 models. This task is very challenging due to the lack of dedicated representations and datasets for learning coherently-connected bricks arrangements, as well as an immense design space that is combinatorial in nature. We approach this task by focusing on creating LEGO® micro buildings. Our contributions are four-fold. First, we propose the LEGO® semantic volume representation to encode LEGO® models, considering the bricks types and bricks connections, while allowing back-propagation learning. Second, we further consider the transformative nature of LEGO ® to atomize the semantic volume and formulate a generative model to learn the representation. Third, we build a rich dataset of micro buildings for model learning. Last, we design the progressive reconstructor to create 3D LEGO® models from the generated representations, while ensuring bricks connections. We employed our pipeline to create LEGO ® micro buildings with a wide array of bricks types, demonstrating its strong capability of learning diverse micro-building styles and producing assemble-able LEGO® models. Further, we performed various quantitative evaluations, ablations, and a user study to show the compelling capability of our approach in terms of generative quality, fidelity, and diversity.

This paper presents a new approach for 3D shape generation, inversion, and manipulation, through a direct generative modeling on a continuous implicit representation in wavelet domain. Specifically, we propose acompact wavelet representationwith a pair of coarse and detail coefficient volumes to implicitly represent 3D shapes via truncated signed distance functions and multi-scale biorthogonal wavelets. Then, we design a pair of neural networks: a diffusion-basedgeneratorto produce diverse shapes in the form of the coarse coefficient volumes and adetail predictorto produce compatible detail coefficient volumes for introducing fine structures and details. Further, we may jointly train anencoder networkto learn a latent space for inverting shapes, allowing us to enable a rich variety of whole-shape and region-aware shape manipulations. Both quantitative and qualitative experimental results manifest the compelling shape generation, inversion, and manipulation capabilities of our approach over the state-of-the-art methods.

Kinesthetic feedback, the feeling of restriction or resistance when hands contact objects, is essential for natural freehand interaction in VR. However, inducing kinesthetic feedback using mechanical hardware can be cumbersome and hard to control in commodity VR systems. We propose the kine-appendage concept to compensate for the loss of kinesthetic feedback in virtual environments, i.e., a virtual appendage is added to the user's avatar hand; when the appendage contacts a virtual object, it exhibits transformations (rotation and deformation); when it disengages from the contact, it recovers its original appearance. A proof-of-concept kine-appendage technique, BrittleStylus, was designed to enhance isomorphic typing. Our empirical evaluations demonstrated that (i) BrittleStylus significantly reduced the uncorrected error rate of naive isomorphic typing from 6.53% to 1.92% without compromising the typing speed; (ii) BrittleStylus could induce the sense of kinesthetic feedback, the degree of which was parity with that induced by pseudo-haptic (+ visual cue) methods; and (iii) participants preferred BrittleStylus over pseudo-haptic (+ visual cue) methods because of not only good performance but also fluent hand movements.

Despite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy. The current best solution is to subsequently employ best models of video SR, denoising, and illumination enhancement, but doing so often lowers the image quality, due to the inconsistency between the models. This paper presents a new parametric representation called the Deep Parametric 3D Filters (DP3DF), which incorporates local spatiotemporal information to enable simultaneous denoising, illumination enhancement, and SR efficiently in a single encoder-and-decoder network. Also, a dynamic residual frame is jointly learned with the DP3DF via a shared backbone to further boost the SR quality. We performed extensive experiments, including a large-scale user study, to show our method's effectiveness. Our method consistently surpasses the best state-of-the-art methods on all the challenging real datasets with top PSNR and user ratings, yet having a very fast run time. The code is available at https://github.com/xiaogang00/DP3DF.

We present Cart, a new approach towards articulatedobject manipulations by human commands. Beyond the existing work that focuses on inferring articulation structures, we further support manipulating articulated shapes to align them subject to simple command templates. The key of Cart is to utilize the prediction of object structures to connect visual observations with user commands for effective manipulations. It is achieved by encoding command messages for motion prediction and a test-time adaptation to adjust the amount of movement from only command supervision. For a rich variety of object categories, Cart can accurately manipulate object shapes and outperform the state-of-the-art approaches in understanding the inherent articulation structures. Also, it can well generalize to unseen object categories and real-world objects. We hope Cart could open new directions for instructing machines to operate articulated objects. Code is available at https://github.com/dvlab-research/Cart.

Real-time 3D hand mesh reconstruction is challenging, especially when the hand is holding some object. Beyond the previous methods, we design H2ONet to fully exploit non-occluded information from multiple frames to boost the reconstruction quality. First, we decouple hand mesh reconstruction into two branches, one to exploit finger-level nonoccluded information and the other to exploit global hand orientation, with lightweight structures to promote real-time inference. Second, we propose finger-level occlusionaware feature fusion, leveraging predicted finger-level occlusion information as guidance to fuse finger-level information across time frames. Further, we design hand-level occlusion-aware feature fusion to fetch non-occluded information from nearby time frames. We conduct experiments on the Dex-YCB and HO3D-v2 datasets with challenging hand-object occlusion cases, manifesting that H2ONet is able to run in real-time and achieves state-of-the-art performance on both the hand mesh and pose precision. The code will be released on GitHub.

Point cloud registration is essential for many applications. However, existing real datasets require extremely tedious and costly annotations, yet may not provide accurate camera poses. For the synthetic datasets, they are mainly object-level, so the trained models may not generalize well to real scenes. We design SIRA-PCR, a new approach to 3D point cloud registration. First, we build a synthetic scene-level 3D registration dataset, specifically designed with physically-based and random strategies to arrange diverse objects. Second, we account for variations in different sensing mechanisms and layout placements, then formulate a sim-to-real adaptation framework with an adaptive re-sample module to simulate patterns in real point clouds. To our best knowledge, this is the first work that explores sim-to-real adaptation for point cloud registration. Extensive experiments show the SOTA performance of SIRA-PCR on widely-used indoor and out-door datasets. The code and dataset will be released on https://github.com/Chen-Suyi/SIRA_Pytorc.h

Unsupervised anomaly detection aims to train models with only anomaly-free images to detect and localize unseen anomalies. Previous reconstruction-based methods have been limited by inaccurate reconstruction results. This work presents a denoising model to detect and localize the anomalies with a generative diffusion model. In particular, we introduce random noise to overwhelm the anomalous pixels and obtain pixel-wise precise anomaly scores from the intermediate denoising process. We find that the KL divergence of the diffusion model serves as a better anomaly score compared with the traditional RGB space score. Furthermore, we reconstruct the features from a pre-trained deep feature extractor as our feature level score to improve localization performance. Moreover, we propose a gradient denoising process to smoothly transform an anomalous image into a normal one. Our denoising model outperforms the state-of-the-art reconstruction-based anomaly detection methods for precise anomaly localization and high-quality normal image reconstruction on the MVTec-AD benchmark.

Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data. To address this issue, we propose SILT, the Shadow-aware Iterative Label Tuning framework, which explicitly considers noise in shadow labels and trains the deep model in a self-training manner. Specifically, we incorporate strong data augmentations with shadow counterfeiting to help the network better recognize non-shadow regions and alleviate overfitting. We also devise a simple yet effective label tuning strategy with global-local fusion and shadow-aware filtering to encourage the network to make significant refinements on the noisy labels. We evaluate the performance of SILT by relabeling the test set of the SBU [55] dataset and conducting various experiments. Our results show that even a simple U-Net [42] trained with SILT can outperform all state-of-the-art methods by a large margin. When trained on SBU / UCF [78] / ISTD [56], our network can successfully reduce the Balanced Error Rate by 25.2% / 36.9% / 21.3% over the best state-of-the-art method.

Instance segmentation is a long-standing task for supporting robotic bin picking. However, objects of diverse classes can be closely packed with occlusions in cluttered and chaotic scenes, hence, even recent methods could have difficulty in locating clear and precise boundaries to distinguish nearby objects. In this work, we aim to improve the boundary quality of the instance masks for robust and precise instance segmentation in these challenging scenarios. Technical-wise, we first formulate an IoU-based Boundary-aware Mask head (IBM head) for predicting the instance-level mask, boundary, and their corresponding IoU scores. With this core module, we then follow the coarse-to-fine strategy and design our pipeline with two stages: an 1IoUNet to learn localization-based objectness cue and a hierarchical mask refiner to produce sharper and cleaner boundaries. We deploy the IBM head throughout the framework. Extensive experimental results on three grasping benchmarks manifest that our method attains the best instance segmentation performance, compared with the state-of-the-art approaches. Practically, we conduct real-world picking tests to show that with the objectness and boundary IoU scores as guidance, we are able to filter invalid (occluded) instances and select high-fidelity (exposed) instances for grasping.

Robotic bin packing is very challenging, especially when considering practical needs such as object variety and packing compactness. This paper presents SDF-Pack, a new approach based on signed distance field (SDF) to model the geometric condition of objects in a container and compute the object placement locations and packing orders for achieving a more compact bin packing. Our method adopts a truncated SDF representation to localize the computation, and based on it, we formulate the SDF -minimization heuristic to find optimized placements to compactly pack objects with the existing ones. To further improve space utilization, if the packing sequence is controllable, our method can suggest which object to be packed next. Experimental results on a large variety of everyday objects show that our method can consistently achieve higher packing compactness over 1,000 packing cases, enabling us to pack more objects into the container, compared with the existing heuristics under various packing settings. The code is publicly available at: https://github.com/kwpoon/SDF-Pack.

We introduce a new diffusion-based approach for shape completion on 3D range scans. Compared with prior deterministic and probabilistic methods, we strike a balance between realism, multi-modality, and high fidelity. We propose DiffComplete by casting shape completion as a generative task conditioned on the incomplete shape. Our key designs are two-fold. First, we devise a hierarchical feature aggregation mechanism to inject conditional features in a spatially-consistent manner. So, we can capture both local details and broader contexts of the conditional inputs to control the shape completion. Second, we propose an occupancy-aware fusion strategy in our model to enable the completion of multiple partial shapes and introduce higher flexibility on the input conditions. DiffComplete sets a new SOTA performance (e.g., 40% decrease on $l_1$ error) on two large-scale 3D shape completion benchmarks. Our completed shapes not only have a realistic outlook compared with the deterministic methods but also exhibit high similarity to the ground truths compared with the probabilistic alternatives. Further, DiffComplete has strong generalizability on objects of entirely unseen classes for both synthetic and real data, eliminating the need for model re-training in various applications.

Few-Shot 3D Point Cloud Object Detection (FS3D) is a challenging task, aiming to detect 3D objects of novel classes using only limited annotated samples for training. Considering that the detection performance highly relies on the quality of the latent features, we design a VAE-based prototype learning scheme, named prototypical VAE (P-VAE), to learn a probabilistic latent space for enhancing the diversity and distinctiveness of the sampled features. The network encodes a multi-center GMM-like posterior, in which each distribution centers at a prototype. For regularization, P-VAE incorporates a reconstruction task to preserve geometric information. To adopt P-VAE for the detection framework, we formulate Geometric-informative Prototypical VAE (GP-VAE) to handle varying geometric components and Class-specific Prototypical VAE (CP-VAE) to handle varying object categories. In the first stage, we harness GP-VAE to aid feature extraction from the input scene. In the second stage, we cluster the geometric-informative features into per-instance features and use CP-VAE to refine each instance feature with category-level guidance. Experimental results show the top performance of our approach over the state of the arts on two FS3D benchmarks. Quantitative ablations and qualitative prototype analysis further demonstrate that our probabilistic modeling can significantly boost prototype learning for FS3D.

This paper presents CLIPXPlore, a new framework that leverages a vision-language model to guide the exploration of the 3D shape space. Many recent methods have been developed to encode 3D shapes into a learned latent shape space to enable generative design and modeling. Yet, existing methods lack effective exploration mechanisms, despite the rich information. To this end, we propose to leverage CLIP, a powerful pre-trained vision-language model, to aid the shape-space exploration. Our idea is threefold. First, we couple the CLIP and shape spaces by generating paired CLIP and shape codes through sketch images and training a mapper network to connect the two spaces. Second, to explore the space around a given shape, we formulate a co-optimization strategy to search for the CLIP code that better matches the geometry of the shape. Third, we design three exploration modes, binary-attribute-guided, text-guided, and sketch-guided, to locate suitable exploration trajectories in shape space and induce meaningful changes to the shape. We perform a series of experiments to quantitatively and visually compare CLIPXPlore with different baselines in each of the three exploration modes, showing that CLIPXPlore can produce many meaningful exploration results that cannot be achieved by the existing solutions.

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.

We present a novel multi-level representation of time series called OM3 that facilitates efficient interactive progressive visualization of large data stored in a database and supports various interactions such as resizing, panning, zooming, and visual query. Based on our proposed line-segment aggregation, this representation can produce error-free line visualizations that preserve the shape of a time series in windows of arbitrary sizes. To reduce the interaction latency, we develop an incremental tree-based query strategy to support progressive visualizations, allowing a finer control on the accuracy-time tradeoff. We quantitatively compare OM3 with state-of-the-art methods, including a method implemented on a leading time-series database InfluxDB, in two settings with databases residing either in the local area network or on the cloud. Results show that OM^3 maintains a low latency within 300~ms on the web browser and a high data reduction ratio regardless of the data size (ranging from millions to billions of records), achieving around 1,000 times faster than the state-of-the-art methods on the largest dataset experimented with.

This paper presents a new text-guided 3D shape generation approach DreamStone that uses images as a stepping stone to bridge the gap between the text and shape modalities for generating 3D shapes without requiring paired text and 3D data. The core of our approach is a two-stage feature-space alignment strategy that leverages a pre-trained single-view reconstruction (SVR) model to map CLIP features to shapes: to begin with, map the CLIP image feature to the detail-rich 3D shape space of the SVR model, then map the CLIP text feature to the 3D shape space through encouraging the CLIP-consistency between the rendered images and the input text. Besides, to extend beyond the generative capability of the SVR model, we design the text-guided 3D shape stylization module that can enhance the output shapes with novel structures and textures. Further, we exploit pre-trained text-to-image diffusion models to enhance the generative diversity, fidelity, and stylization capability. Our approach is generic, flexible, and scalable. It can be easily integrated with various SVR models to expand the generative space and improve the generative fidelity. Extensive experimental results demonstrate that our approach outperforms the state-of-the-art methods in terms of generative quality and consistency with the input text.

This article formulates a new problem, instance shadow detection, which aims to detect shadow instance and the associated object instance that cast each shadow in the input image. To approach this task, we first compile a new dataset with the masks for shadow instances, object instances, and shadow-object associations. We then design an evaluation metric for quantitative evaluation of the performance of instance shadow detection. Further, we design a single-stage detector to perform instance shadow detection in an end-to-end manner, where the bidirectional relation learning module and the deformable maskIoU head are proposed in the detector to directly learn the relation between shadow instances and object instances and to improve the accuracy of the predicted masks. Finally, we quantitatively and qualitatively evaluate our method on the benchmark dataset of instance shadow detection and show the applicability of our method on light direction estimation and photo editing.

This paper presents a new text-guided technique for generating 3D shapes. The technique leverages a hybrid 3D shape representation, namely EXIM, combining the strengths of explicit and implicit representations. Specifically, the explicit stage controls the topology of the generated 3D shapes and enables local modifications, whereas the implicit stage refines the shape and paints it with plausible colors. Also, the hybrid approach separates the shape and color and generates color conditioned on shape to ensure shape-color consistency. Unlike the existing state-of-the-art methods, we achieve high-fidelity shape generation from natural-language descriptions without the need for time-consuming per-shape optimization or reliance on human-annotated texts during training or test-time optimization. Further, we demonstrate the applicability of our approach to generate indoor scenes with consistent styles using text-induced 3D shapes. Through extensive experiments, we demonstrate the compelling quality of our results and the high coherency of our generated shapes with the input texts, surpassing the performance of existing methods by a significant margin. Codes and models are released at https://github.com/liuzhengzhe/EXIM.

This paper presents computational methods to aid the creation of LEGO ®1 sketch models from simple input images. Beyond conventional LEGO ® mosaics, we aim to improve the expressiveness of LEGO ® models by utilizing LEGO ® tiles with sloping and rounding edges, together with rectangular bricks, to reproduce smooth curves and sharp features in the input. This is a challenging task, as we have limited brick shapes to use and limited space to place bricks. Also, the search space is immense and combinatorial in nature. We approach the task by decoupling the LEGO ® construction into two steps: first approximate the shape with a LEGO ® -buildable contour then filling the contour polygon with LEGO ® bricks. Further, we formulate this contour approximation into a graph optimization with our objective and constraints and effectively solve for the contour polygon that best approximates the input shape. Further, we extend our optimization model to handle multi-color and multi-layer regions, and formulate a grid alignment process and various perceptual constraints to refine the results. We employ our method to create a large variety of LEGO ® models and compare it with humans and baseline methods to manifest its compelling quality and speed.

This work presents an innovative method for point set self-embedding, that encodes the structural information of a dense point set into its sparser version in a visual but imperceptible form. The self-embedded point set can function as the ordinary downsampled one and be visualized efficiently on mobile devices. Particularly, we can leverage the self-embedded information to fully restore the original point set for detailed analysis on remote servers. This task is challenging, since both the self-embedded point set and the restored point set should resemble the original one. To achieve a learnable self-embedding scheme, we design a novel framework with two jointly-trained networks: one to encode the input point set into its self-embedded sparse point set and the other to leverage the embedded information for inverting the original point set back. Further, we develop a pair of up-shuffle and down-shuffle units in the two networks, and formulate loss terms to encourage the shape similarity and point distribution in the results. Extensive qualitative and quantitative results demonstrate the effectiveness of our method on both synthetic and real-scanned datasets. The source code and trained models will be publicly available at https://github.com/liruihui/Self-Embedding.

We present a novel two-stage approach for automated floorplan design in residential buildings with a given exterior wall boundary. Our approach has the unique advantage of being human-centric, that is, the generated floorplans can be geometrically plausible, as well as topologically reasonable to enhance resident interaction with the environment. From the input boundary, we first synthesize a human-activity map that reflects both the spatial configuration and human-environment interaction in an architectural space. We propose to produce the human-activity map either automatically by a pre-trained generative adversarial network (GAN) model, or semi-automatically by synthesizing it with user manipulation of the furniture. Second, we feed the human-activity map into our deep framework ActFloor-GAN to guide a pixel-wise prediction of room types. We adopt a re-formulated cycle-consistency constraint in ActFloor-GAN to maximize the overall prediction performance, so that we can produce high-quality room layouts that are readily convertible to vectorized floorplans. Experimental results show several benefits of our approach. First, a quantitative comparison with prior methods shows superior performance of leveraging the human-activity map in predicting piecewise room types. Second, a subjective evaluation by architects shows that our results have compelling quality as professionally-designed floorplans and much better than those generated by existing methods in terms of the room layout topology. Last, our approach allows manipulating the furniture placement, considers the human activities in the environment, and enables the incorporation of user-design preferences.

We explore the way to alleviate the label-hungry problem in a semi-supervised setting for 3D instance segmentation. To leverage the unlabeled data to boost model performance, we present a novel Two-Way Inter-label Self-Training framework named TWIST. It exploits inherent correlations between semantic understanding and instance information of a scene. Specifically, we consider two kinds of pseudo labels for semantic- and instance-level supervision. Our key design is to provide object-level information for denoising pseudo labels and make use of their correlation for two-way mutual enhancement, thereby iteratively promoting the pseudo-label qualities. TWIST attains leading performance on both ScanNet and S3DIS, compared to recent 3D pre-training approaches, and can cooperate with them to further enhance performance, e.g., +4.4% AP50on 1%-label ScanNet data-efficient benchmark. Code is available at https://github.com/dvlab-research/TWIST.

This paper introduces a novel framework called DTNet for 3D mesh reconstruction and generation via Disentangled Topology. Beyond previous works, we learn a topology-aware neural template specific to each input then deform the template to reconstruct a detailed mesh while preserving the learned topology. One key insight is to decouple the complex mesh reconstruction into two sub-tasks: topology formulation and shape deformation. Thanks to the decoupling, DT-Net implicitly learns a disentangled representation for the topology and shape in the latent space. Hence, it can enable novel disentangled controls for supporting various shape generation applications, e.g., remix the topologies of 3D objects, that are not achievable by previous reconstruction works. Extensive experimental results demonstrate that our method11Code available at https://github.com/edward1997104/Neural-Template. is able to produce high-quality meshes, particularly with diverse topologies, as compared with the state-of-the-art methods.

In this work, we explore the challenging task of generating 3D shapes from text. Beyond the existing works, we propose a new approach for text-guided 3D shape generation, capable of producing high-fidelity shapes with colors that match the given text description. This work has several technical contributions. First, we decouple the shape and color predictions for learning features in both texts and shapes, and propose the word-level spatial transformer to correlate word features from text with spatial features from shape. Also, we design a cyclic loss to encourage consistency between text and shape, and introduce the shape IMLE to diversify the generated shapes. Further, we extend the framework to enable text-guided shape manipulation. Extensive experiments on the largest existing text-shape benchmark [10] manifest the superiority of this work. The code and the models are available at https://github.com/liuzhengzhe/Towards-Implicit-Text-Guided-Shape-Generation.

This paper presents a new solution for low-light image enhancement by collectively exploiting Signal-to-Noise-Ratio-aware transformers and convolutional models to dynamically enhance pixels with spatial-varying operations. They are long-range operations for image regions of extremely low Signal-to-Noise-Ratio (SNR) and short-range operations for other regions. We propose to take an SNR prior to guide the feature fusion and formulate the SNR-aware transformer with a new self-attention model to avoid tokens from noisy image regions of very low SNR. Extensive experiments show that our framework consistently achieves better performance than SOTA approaches on seven representative benchmarks with the same structure. Also, we conducted a large-scale user study with 100 participants to verify the superior perceptual quality of our results. The code is available at https://github.com/dvlab-research/SNR-Aware-Low-Light-Enhance.

This paper presents a new approach to boost a single-modality (LiDAR) 3D object detector by teaching it to sim-ulate features and responses that follow a multi-modality (LiDAR-image) detector. The approach needs LiDAR-image data only when training the single-modality detector, and once well-trained, it only needs LiDAR data at inference. We design a novel framework to realize the approach: re-sponse distillation to focus on the crucial response samples and avoid most background samples; sparse-voxel distillation to learn voxel semantics and relations from the esti-mated crucial voxels; a fine-grained voxel-to-point distillation to better attend to features of small and distant objects; and instance distillation to further enhance the deep-feature consistency. Experimental results on the nuScenes dataset show that our approach outperforms all SOTA LiDAR-only 3D detectors and even surpasses the baseline LiDAR-image detector on the key NDS metric, filling ~72% mAP gap be-tween the single- and multi-modality detectors.

Industrial bin picking is a challenging task that requires accurate and robust segmentation of individual object instances. Particularly, industrial objects can have irregular shapes, that is, thin and concave, whereas in bin-picking scenarios, objects are often closely packed with strong occlusion. To address these challenges, we formulate a novel part-aware instance segmentation pipeline. The key idea is to decompose industrial objects into correlated approximate convex parts and enhance the object-level segmentation with part-level segmentation. We design a part-aware network to predict part masks and part-to-part offsets, followed by a part aggregation module to assemble the recognized parts into instances. To guide the network learning, we also propose an automatic label decoupling scheme to generate ground-truth part-level labels from instance-level labels. Finally, we contribute the first instance segmentation dataset, which contains a variety of industrial objects that are thin and have non-trivial shapes. Extensive experimental results on various industrial objects demonstrate that our method can achieve the best segmentation results compared with the state-of-the-art approaches.

Instance segmentation is an important task for supporting robotic grasping in auto-store scenarios. Accurate segmentation usually relies on the quantity and quality of available annotated training data. However, it requires tremendous cost to obtain these labels. In this work, without requiring any human annotations on real data, our proposed self-ensembling sim-to-real network, namely SESR, is able to generate precise instance masks for a wide variety of supermarket goods. We design our SESR with a teacher model and a student model trained with a self-ensembling strategy. We adopt different levels of consistency to bridge the sim-to-real gap and boost the model generalization ability. Also, we compile an auto-store bin-picking dataset covering various goods. Extensive experiments on both unseen scenarios and unseen objects validate the effectiveness and superiority of our method over others, and the robot arm demonstrations further show that our segmentation results can support real-time auto-store bin picking.

To boost a detector for single-frame 3D object detection, we present a new approach to train it to simulate features and responses following a detector trained on multi-frame point clouds. Our approach needs multi-frame point clouds only when training the single-frame detector, and once trained, it can detect objects with only single-frame point clouds as inputs during the inference. For this purpose, we design a novel Simulated Multi-Frame Single-Stage object Detector (SMF-SSD) framework: multi-view dense object fusion to densify ground-truth objects to generate a multi-frame point cloud; self-attention voxel distillation to facilitate one-to-many knowledge transfer from multi- to single-frame voxels; multi-scale BEV feature distillation to transfer knowledge in low-level spatial and high-level semantic BEV features; and adaptive response distillation to activate single-frame responses of high confidence and accurate localization. Experimental results on the Waymo test set show that our SMF-SSD consistently outperforms all state-of-the-art single-frame 3D object detectors for all object classes of difficulty levels 1 and 2 in terms of both mAP and mAPH.

LiDAR-produced point clouds are the major source for most state-of-the-art 3D object detectors. Yet, small, distant, and incomplete objects with sparse or few points are often hard to detect. We present Sparse2Dense, a new framework to efficiently boost 3D detection performance by learning to densify point clouds in latent space. Specifically, we first train a dense point 3D detector (DDet) with a dense point cloud as input and design a sparse point 3D detector (SDet) with a regular point cloud as input. Importantly, we formulate the lightweight plug-in S2D module and the point cloud reconstruction module in SDet to densify 3D features and train SDet to produce 3D features, following the dense 3D features in DDet. So, in inference, SDet can simulate dense 3D features from regular (sparse) point cloud inputs without requiring dense inputs. We evaluate our method on the large-scale Waymo Open Dataset and the Waymo Domain Adaptation Dataset, showing its high performance and efficiency over the state of the arts.

This paper presents a new approach for 3D shape generation, enabling direct generative modeling on a continuous implicit representation in wavelet domain. Specifically, we propose a compact wavelet representation with a pair of coarse and detail coefficient volumes to implicitly represent 3D shapes via truncated signed distance functions and multi-scale biorthogonal wavelets, and formulate a pair of neural networks: a generator based on the diffusion model to produce diverse shapes in the form of coarse coefficient volumes; and a detail predictor to further produce compatible detail coefficient volumes for enriching the generated shapes with fine structures and details. Both quantitative and qualitative experimental results manifest the superiority of our approach in generating diverse and high-quality shapes with complex topology and structures, clean surfaces, and fine details, exceeding the 3D generation capabilities of the state-of-the-art models.

Abstract We study structural rigidity for assemblies with mechanical joints. Existing methods identify whether an assembly is structurally rigid by assuming parts are perfectly rigid. Yet, an assembly identified as rigid may not be that “rigid” in practice, and existing methods cannot quantify how rigid an assembly is. We address this limitation by developing a new measure, worst‐case rigidity, to quantify the rigidity of an assembly as the largest possible deformation that the assembly undergoes for arbitrary external loads of fixed magnitude. Computing worst‐case rigidity is non‐trivial due to non‐rigid parts and different joint types. We thus formulate a new computational approach by encoding parts and their connections into a stiffness matrix, in which parts are modeled as deformable objects and joints as soft constraints. Based on this, we formulate worst‐case rigidity analysis as an optimization that seeks the worst‐case deformation of an assembly for arbitrary external loads, and solve the optimization problem via an eigenanalysis. Furthermore, we present methods to optimize the geometry and topology of various assemblies to enhance their rigidity, as guided by our rigidity measure. In the end, we validate our method on a variety of assembly structures with physical experiments and demonstrate its effectiveness by designing and fabricating several structurally rigid assemblies.

We introduce the first learning-based reconstructability predictor to improve view and path planning for large-scale 3D urban scene acquisition using unmanned drones. In contrast to previous heuristic approaches, our method learns a model that explicitly predicts how well a 3D urban scene will be reconstructed from a set of viewpoints. To make such a model trainable and simultaneously applicable to drone path planning, we simulate the proxy-based 3D scene reconstruction during training to set up the prediction. Specifically, the neural network we design is trained to predict the scene reconstructability as a function of the proxy geometry , a set of viewpoints, and optionally a series of scene images acquired in flight. To reconstruct a new urban scene, we first build the 3D scene proxy, then rely on the predicted reconstruction quality and uncertainty measures by our network, based off of the proxy geometry, to guide the drone path planning. We demonstrate that our data-driven reconstructability predictions are more closely correlated to the true reconstruction quality than prior heuristic measures. Further, our learned predictor can be easily integrated into existing path planners to yield improvements. Finally, we devise a new iterative view planning framework, based on the learned reconstructability, and show superior performance of the new planner when reconstructing both synthetic and real scenes.

We present a pyramid-based scatterplot sampling technique to avoid overplotting and enable progressive and streaming visualization of large data. Our technique is based on a multiresolution pyramid-based decomposition of the underlying density map and makes use of the density values in the pyramid to guide the sampling at each scale for preserving the relative data densities and outliers. We show that our technique is competitive in quality with state-of-the-art methods and runs faster by about an order of magnitude. Also, we have adapted it to deliver progressive and streaming data visualization by processing the data in chunks and updating the scatterplot areas with visible changes in the density map. A quantitative evaluation shows that our approach generates stable and faithful progressive samples that are comparable to the state-of-the-art method in preserving relative densities and superior to it in keeping outliers and stability when switching frames. We present two case studies that demonstrate the effectiveness of our approach for exploring large data.

Recently, many deep neural networks were designed to process 3D point clouds, but a common drawback is that rotation invariance is not ensured, leading to poor generalization to arbitrary orientations. In this article, we introduce a new low-level purely rotation-invariant representation to replace common 3D Cartesian coordinates as the network inputs. Also, we present a network architecture to embed these representations into features, encoding local relations between points and their neighbors, and the global shape structure. To alleviate inevitable global information loss caused by the rotation-invariant representations, we further introduce a region relation convolution to encode local and non-local information. We evaluate our method on multiple point cloud analysis tasks, including (i) shape classification, (ii) part segmentation, and (iii) shape retrieval. Extensive experimental results show that our method achieves consistent, and also the best performance, on inputs at arbitrary orientations, compared with all the state-of-the-art methods.

This article presents a new approach based on deep learning to automatically extract colormaps from visualizations. After summarizing colors in an input visualization image as a Lab color histogram, we pass the histogram to a pre-trained deep neural network, which learns to predict the colormap that produces the visualization. To train the network, we create a new dataset of ∼ 64K visualizations that cover a wide variety of data distributions, chart types, and colormaps. The network adopts an atrous spatial pyramid pooling module to capture color features at multiple scales in the input color histograms. We then classify the predicted colormap as discrete or continuous, and refine the predicted colormap based on its color histogram. Quantitative comparisons to existing methods show the superior performance of our approach on both synthetic and real-world visualizations. We further demonstrate the utility of our method with two use cases, i.e., color transfer and color remapping.

Time-series data-usually presented in the form of lines-plays an important role in many domains such as finance, meteorology, health, and urban informatics. Yet, little has been done to support interactive exploration of large-scale time-series data, which requires a clutter-free visual representation with low-latency interactions. In this paper, we contribute a novel line-segment-based KD-tree method to enable interactive analysis of many time series. Our method enables not only fast queries over time series in selected regions of interest but also a line splatting method for efficient computation of the density field and selection of representative lines. Further, we develop KD-Box, an interactive system that provides rich interactions, e.g., timebox, attribute filtering, and coordinated multiple views. We demonstrate the effectiveness of KD-Box in supporting efficient line query and density field computation through a quantitative comparison and show its usefulness for interactive visual analysis on several real-world datasets.

Existing single-stage detectors for locating objects in point clouds often treat object localization and category classification as separate tasks, so the localization accuracy and classification confidence may not well align. To address this issue, we present a new single-stage detector named the Confident IoU-Aware Single-Stage object Detector (CIA-SSD). First, we design the lightweight Spatial-Semantic Feature Aggregation module to adaptively fuse high-level abstract semantic features and low-level spatial features for accurate predictions of bounding boxes and classification confidence. Also, the predicted confidence is further rectified with our designed IoU-aware confidence rectification module to make the confidence more consistent with the localization accuracy. Based on the rectified confidence, we further formulate the Distance-variant IoU-weighted NMS to obtain smoother regressions and avoid redundant predictions. We experiment CIA-SSD on 3D car detection in the KITTI test set and show that it attains top performance in terms of the official ranking metric (moderate AP 80.28%) and above 32 FPS inference speed, outperforming all prior single-stage detectors. The code is available at https://github.com/Vegeta2020/CIA-SSD.

Instance shadow detection aims to find shadow instances paired with the objects that cast the shadows. The previous work adopts a two-stage framework to first predict shadow instances, object instances, and shadow-object associations from the region proposals, then leverage a post-processing to match the predictions to form the final shadow-object pairs. In this paper, we present a new single-stage fully-convolutional network architecture with a bidirectional relation learning module to directly learn the relations of shadow and object instances in an end-to-end manner. Compared with the prior work, our method actively explores the internal relationship between shadows and objects to learn a better pairing between them, thus improving the overall performance for instance shadow detection. We evaluate our method on the benchmark dataset for instance shadow detection, both quantitatively and visually. The experimental results demonstrate that our method clearly outperforms the state-of-the-art method.

Point clouds produced by 3D scanning are often sparse, non-uniform, and noisy. Recent upsampling approaches aim to generate a dense point set, while achieving both distribution uniformity and proximity-to-surface, and possibly amending small holes, all in a single network. After revisiting the task, we propose to disentangle the task based on its multi-objective nature and formulate two cascaded sub-networks, a dense generator and a spatial refiner. The dense generator infers a coarse but dense out-put that roughly describes the underlying surface, while the spatial refiner further fine-tunes the coarse output by adjusting the location of each point. Specifically, we design a pair of local and global refinement units in the spatial refiner to evolve a coarse feature map. Also, in the spatial refiner, we regress a per-point offset vector to further adjust the coarse outputs in fine scale. Extensive qualitative and quantitative results on both synthetic and real-scanned datasets demonstrate the superiority of our method over the state-of-the-arts. The code is publicly available at https://github.com/liruihui/Dis-PU.

Point cloud semantic segmentation often requires large-scale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take the approach to an extreme and propose "One Thing One Click," meaning that the annotator only needs to label one point per object. To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, facilitated by a graph propagation module. Also, we adopt a relation network to generate the per-category prototype and explicitly model the similarity among graph nodes to generate pseudo labels to guide the iterative training. Experimental results on both ScanNet-v2 and S3DIS show that our self-training approach, with extremely-sparse annotations, outperforms all existing weakly supervised methods for 3D semantic segmentation by a large margin, and our results are also comparable to those of the fully supervised counterparts.

Indoor scene semantic parsing from RGB images is very challenging due to occlusions, object distortion, and view-point variations. Going beyond prior works that leverage geometry information, typically paired depth maps, we present a new approach, a 3D-to-2D distillation framework, that enables us to leverage 3D features extracted from large-scale 3D data repositories (e.g., ScanNet-v2) to enhance 2D features extracted from RGB images. Our work has three novel contributions. First, we distill 3D knowledge from a pretrained 3D network to supervise a 2D network to learn simulated 3D features from 2D features during the training, so the 2D network can infer without requiring 3D data. Second, we design a two-stage dimension normalization scheme to calibrate the 2D and 3D features for better integration. Third, we design a semantic-aware adversarial training model to extend our framework for training with un-paired 3D data. Extensive experiments on various datasets, ScanNet-V2, S3DIS, and NYU-v2, demonstrate the superiority of our approach. Also, experimental results show that our 3D-to-2D distillation improves the model generalization.

We present Self-Ensembling Single-Stage object Detector (SE-SSD) for accurate and efficient 3D object detection in outdoor point clouds. Our key focus is on exploiting both soft and hard targets with our formulated constraints to jointly optimize the model, without introducing extra computation in the inference. Specifically, SE-SSD contains a pair of teacher and student SSDs, in which we design an effective IoU-based matching strategy to filter soft targets from the teacher and formulate a consistency loss to align student predictions with them. Also, to maximize the distilled knowledge for ensembling the teacher, we design a new augmentation scheme to produce shape-aware augmented samples to train the student, aiming to encourage it to infer complete object shapes. Lastly, to better exploit hard targets, we design an ODIoU loss to supervise the student with constraints on the predicted box centers and orientations. Our SE-SSD attains top performance compared with all prior published works. Also, it attains top precisions for car detection in the KITTI benchmark (ranked 1stand 2ndon the BEV and 3D leaderboards1, respectively) with an ultra-high inference speed. The code is available at https://github.com/Vegeta2020/SE-SSD.

Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the high cost and challenges of 3D point-level labeling, we present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance. Inspired by the recent contrastive loss in self-supervised tasks, we propose the guided point contrastive loss to enhance the feature representation and model generalization ability in semi-supervised setting. Semantic predictions on unlabeled point clouds serve as pseudo-label guidance in our loss to avoid negative pairs in the same category. Also, we design the confidence guidance to ensure high-quality feature learning. Besides, a category-balanced sampling strategy is proposed to collect positive and negative samples to mitigate the class imbalance problem. Extensive experiments on three datasets (ScanNet V2, S3DIS, and SemanticKITTI) show the effectiveness of our semi-supervised method to improve the prediction quality with unlabeled data.

3D hand-mesh reconstruction from RGB images facilitates many applications, including augmented reality (AR). However, this requires not only real-time speed and accurate hand pose and shape but also plausible mesh-image alignment. While existing works already achieve promising results, meeting all three requirements is very challenging. This paper presents a novel pipeline by decoupling the hand-mesh reconstruction task into three stages: a joint stage to predict hand joints and segmentation; a mesh stage to predict a rough hand mesh; and a refine stage to fine-tune it with an offset mesh for mesh-image alignment. With careful design in the network structure and in the loss functions, we can promote high-quality finger-level mesh-image alignment and drive the models together to deliver real-time predictions. Extensive quantitative and qualitative results on benchmark datasets demonstrate that the quality of our results outperforms the state-of-the-art methods on hand-mesh/pose precision and hand-image alignment. In the end, we also showcase several real-time AR scenarios.

Low-light video enhancement is an important task. Previous work is mostly trained on paired static images or videos. We compile a new dataset formed by our new strategy that contains high-quality spatially-aligned video pairs from dynamic scenes in low- and normal-light conditions. We built it using a mechatronic system to precisely control the dynamics during the video capture process, and further align the video pairs, both spatially and temporally, by identifying the system’s uniform motion stage. Besides the dataset, we propose an end-to-end framework, in which we design a self-supervised strategy to reduce noise, while enhancing the illumination based on the Retinex theory. Extensive experiments based on various metrics and large-scale user study demonstrate the value of our dataset and effectiveness of our method. The dataset and code are available at https://github.com/dvlab-research/SDSD.

Video prediction methods generally consume substantial computing resources in training and deployment, among which keypoint-based approaches show promising improvement in efficiency by simplifying dense image prediction to light keypoint prediction. However, keypoint locations are often modeled only as continuous coordinates, so noise from semantically insignificant deviations in videos easily disrupt learning stability, leading to inaccurate keypoint modeling. In this paper, we design a new grid keypoint learning framework, aiming at a robust and explainable intermediate keypoint representation for long-term efficient video prediction. We have two major technical contributions. First, we detect keypoints by jumping among candidate locations in our raised grid space and formulate a condensation loss to encourage meaningful keypoints with strong representative capability. Second, we introduce a 2D binary map to represent the detected grid keypoints and then suggest propagating keypoint locations with stochasticity by selecting entries in the discrete grid space, thus preserving the spatial structure of keypoints in the long-term horizon for better future frame generation. Extensive experiments verify that our method outperforms the state-of-the-art stochastic video prediction methods while saves more than 98% of computing resources. We also demonstrate our method on a robotic-assisted surgery dataset with promising results. Our code is available at https://github.com/xjgaocs/Grid-Keypoint-Learning.

Abstract We introduce the curve complexity heuristic (CCH), a KD‐tree construction strategy for 3D curves, which enables interactive exploration of neighborhoods in dense and large line datasets. It can be applied to searches of k‐nearest curves (KNC) as well as radius‐nearest curves (RNC). The CCH KD‐tree construction consists of two steps: (i) 3D curve decomposition that takes into account curve complexity and (ii) KD‐tree construction, which involves a novel splitting and early termination strategy. The obtained KD‐tree allows us to improve the speed of existing neighborhood search approaches by at least an order of magnitude (i. e., 28×for KNC and 12×for RNC with 98% accuracy) by considering local curve complexity. We validate this performance with a quantitative evaluation of the quality of search results and computation time. Also, we demonstrate the usefulness of our approach for supporting various applications such as interactive line queries, line opacity optimization, and line abstraction.

This paper presents a new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects. Our key idea is to adaptively propagate and aggregate the image context features with variable attenuation over the entire feature maps. To achieve this, we design the spatial attenuation context (SAC) module to recurrently translate and aggregate the context features independently with different attenuation factors and then to attentively learn the weights to adaptively integrate the aggregated context features. By further embedding the module to process individual layers in a deep network, namely SAC-Net, we can train the network end-To-end and optimize the context features for detecting salient objects. Compared with 29 state-of-The-Art methods, experimental results show that our method performs favorably over all the others on six common benchmark data, both quantitatively and visually.

Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations.

Rain is a common weather phenomenon that affects environmental monitoring and surveillance systems. According to an established rain model (Garg and Nayar, 2007), the scene visibility in the rain varies with the depth from the camera, where objects faraway are visually blocked more by the fog than by the rain streaks. However, existing datasets and methods for rain removal ignore these physical properties, thus limiting the rain removal efficiency on real photos. In this work, we analyze the visual effects of rain subject to scene depth and formulate a rain imaging model that collectively considers rain streaks and fog. Also, we prepare a dataset called RainCityscapes on real outdoor photos. Furthermore, we design a novel real-time end-to-end deep neural network, for which we train to learn the depth-guided non-local features and to regress a residual map to produce a rain-free output image. We performed various experiments to visually and quantitatively compare our method with several state-of-the-art methods to show its superiority over others.

The ability to recognize the position and order of the floor-level lines that divide adjacent building floors can benefit many applications, for example, urban augmented reality (AR). This work tackles the problem of locating floor-level lines in street-view images, using a supervised deep learning approach. Unfortunately, very little data is available for training such a network - current street-view datasets contain either semantic annotations that lack geometric attributes, or rectified facades without perspective priors. To address this issue, we first compile a new dataset and develop a new data augmentation scheme to synthesize training samples by harassing (i) the rich semantics of existing rectified facades and (ii) perspective priors of buildings in diverse street views. Next, we design FloorLevel-Net, a multi-task learning network that associates explicit features of building facades and implicit floor-level lines, along with a height-attention mechanism to help enforce a vertical ordering of floor-level lines. The generated segmentations are then passed to a second-stage geometry post-processing to exploit self-constrained geometric priors for plausible and consistent reconstruction of floor-level lines. Quantitative and qualitative evaluations conducted on assorted facades in existing datasets and street views from Google demonstrate the effectiveness of our approach. Also, we present context-aware image overlay results and show the potentials of our approach in enriching AR-related applications. Project website: https://wumengyangok.github.io/Project/FloorLevelNet.

A common shortfall of supervised deep learning for medical imaging is the lack of labeled data, which is often expensive and time consuming to collect. This article presents a new semisupervised method for medical image segmentation, where the network is optimized by a weighted combination of a common supervised loss only for the labeled inputs and a regularization loss for both the labeled and unlabeled data. To utilize the unlabeled data, our method encourages consistent predictions of the network-in-training for the same input under different perturbations. With the semisupervised segmentation tasks, we introduce a transformation-consistent strategy in the self-ensembling model to enhance the regularization effect for pixel-level predictions. To further improve the regularization effects, we extend the transformation in a more generalized form including scaling and optimize the consistency loss with a teacher model, which is an averaging of the student model weights. We extensively validated the proposed semisupervised method on three typical yet challenging medical image segmentation tasks: 1) skin lesion segmentation from dermoscopy images in the International Skin Imaging Collaboration (ISIC) 2017 data set; 2) optic disk (OD) segmentation from fundus images in the Retinal Fundus Glaucoma Challenge (REFUGE) data set; and 3) liver segmentation from volumetric CT scans in the Liver Tumor Segmentation Challenge (LiTS) data set. Compared with state-of-the-art, our method shows superior performance on the challenging 2-D/3-D medical images, demonstrating the effectiveness of our semisupervised method for medical image segmentation.

We present SP-GAN, a new unsupervised sphere-guided generative model for direct synthesis of 3D shapes in the form of point clouds. Compared with existing models, SP-GAN is able to synthesize diverse and high-quality shapes with fine details and promote controllability for part-aware shape generation and manipulation, yet trainable without any parts annotations. In SP-GAN, we incorporate a global prior (uniform points on a sphere) to spatially guide the generative process and attach a local prior (a random latent code) to each sphere point to provide local details. The key insight in our design is to disentangle the complex 3D shape generation task into a global shape modeling and a local structure adjustment, to ease the learning process and enhance the shape generation quality. Also, our model forms an implicit dense correspondence between the sphere points and points in every generated shape, enabling various forms of structure-aware shape manipulations such as part editing, part-wise shape interpolation, and multi-shape part composition, etc., beyond the existing generative models. Experimental results, which include both visual and quantitative evaluations, demonstrate that our model is able to synthesize diverse point clouds with fine details and less noise, as compared with the state-of-the-art models.

We introduce the first path-oriented drone trajectory planning algorithm, which performs continuous (i.e., dense ) image acquisition along an aerial path and explicitly factors path quality into an optimization along with scene reconstruction quality. Specifically, our method takes as input a rough 3D scene proxy and produces a drone trajectory and image capturing setup, which efficiently yields a high-quality reconstruction of the 3D scene based on three optimization objectives: one to maximize the amount of 3D scene information that can be acquired along the entirety of the trajectory, another to optimize the scene capturing efficiency by maximizing the scene information that can be acquired per unit length along the aerial path, and the last one to minimize the total turning angles along the aerial path, so as to reduce the number of sharp turns. Our search scheme is based on the rapidly-exploring random tree framework, resulting in a final trajectory as a single path through the search tree. Unlike state-of-the-art works, our joint optimization for view selection and path planning is performed in a single step. We comprehensively evaluate our method not only on benchmark virtual datasets as in existing works but also on several large-scale real urban scenes. We demonstrate that the continuous paths optimized by our method can effectively reduce onsite acquisition cost using drones, while achieving high-fidelity 3D reconstruction, compared to existing planning methods and oblique photography, a mature and popular industry solution.

This article presents a deep normal filtering network, called DNF-Net, for mesh denoising. To better capture local geometry, our network processes the mesh in terms of local patches extracted from the mesh. Overall, DNF-Net is an end-to-end network that takes patches of facet normals as inputs and directly outputs the corresponding denoised facet normals of the patches. In this way, we can reconstruct the geometry from the denoised normals with feature preservation. Besides the overall network architecture, our contributions include a novel multi-scale feature embedding unit, a residual learning strategy to remove noise, and a deeply-supervised joint loss function. Compared with the recent data-driven works on mesh denoising, DNF-Net does not require manual input to extract features and better utilizes the training data to enhance its denoising performance. Finally, we present comprehensive experiments to evaluate our method and demonstrate its superiority over the state of the art on both synthetic and real-scanned meshes.

Selecting targets directly in the virtual world is difficult due to the lack of haptic feedback and inaccurate estimation of egocentric distances. Proprioception, the sense of self-movement and body position, can be utilized to improve virtual target selection by placing targets on or around one's body. However, its effective scope is limited closely around one's body. We explore the concept of virtually-extended proprioception by appending virtual body parts mimicking real body parts to users' avatars, to provide spatial reference to virtual targets. Our studies suggest that our approach facilitates more efficient target selection in VR as compared to no reference or using an everyday object as reference. Besides, by cultivating users' sense of ownership on the appended virtual body part, we can further enhance target selection performance. The effects of transparency and granularity of the virtual body part on target selection performance are also discussed.

Instance segmentation is an important task for scene understanding. Compared to the fully-developed 2D, 3D instance segmentation for point clouds have much room to improve. In this paper, we present PointGroup, a new end-to-end bottom-up architecture, specifically focused on better grouping the points by exploring the void space between objects. We design a two-branch network to extract point features and predict semantic labels and offsets, for shifting each point towards its respective instance centroid. A clustering component is followed to utilize both the original and offset-shifted point coordinate sets, taking advantage of their complementary strength. Further, we formulate the ScoreNet to evaluate the candidate instances, followed by the Non-Maximum Suppression (NMS) to remove duplicates. We conduct extensive experiments on two challenging datasets, ScanNet v2 and S3DIS, on which our method achieves the highest performance, 63.6% and 64.0%, compared to 54.9% and 54.4% achieved by former best solutions in terms of mAP with IoU threshold 0.5.

We present PointAugment, a new auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network. Different from existing auto-augmentation methods for 2D images, PointAugment is sample-aware and takes an adversarial learning strategy to jointly optimize an augmentor network and a classifier network, such that the augmentor can learn to produce augmented samples that best fit the classifier. Moreover, we formulate a learnable point augmentation function with a shape-wise transformation and a point-wise displacement, and carefully design loss functions to adopt the augmented samples based on the learning progress of the classifier. Extensive experiments also confirm PointAugment's effectiveness and robustness to improve the performance of various networks on shape classification and retrival.

Instance shadow detection is a brand new problem, aiming to find shadow instances paired with object instances. To approach it, we first prepare a new dataset called SOBA, named after Shadow-OBject Association, with 3,623 pairs of shadow and object instances in 1,000 photos, each with individual labeled masks. Second, we design LISA, named after Light-guided Instance Shadow-object Association, an end-to-end framework to automatically predict the shadow and object instances, together with the shadow-object associations and light direction. Then, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results. In our evaluations, we formulate a new metric named the shadow-object average precision to measure the performance of our results. Further, we conducted various experiments and demonstrate our method's applicability on light direction estimation and photo editing.

Existing augmented reality (AR) applications often ignore the occlusion between real hands and virtual objects when incorporating virtual objects in user's views. The challenges come from the lack of accurate depth and mismatch between real and virtual depth. This paper presents GrabAR1, a new approach that directly predicts the real-and-virtual occlusion and bypasses the depth acquisition and inference. Our goal is to enhance AR applications with interactions between hand (real) and grabbable objects (virtual). With paired images of hand and object as inputs, we formulate a compact deep neural network that learns to generate the occlusion mask. To train the network, we compile a large dataset, including synthetic data and real data. We then embed the trained network in a prototyping AR system to support real-time grabbing of virtual objects. Further, we demonstrate the performance of our method on various virtual objects, compare our method with others through two user studies, and showcase a rich variety of interaction scenarios, in which we can use bare hand to grab virtual objects and directly manipulate them.

Abstract We study a general form of gears known as non‐circular gears that can transfer periodic motion with variable speed through their irregular shapes and eccentric rotation centers. To design functional non‐circular gears is nontrivial, since the gear pair must have compatible shape to keep in contact during motion, so the driver gear can push the follower to rotate via a bounded torque that the motor can exert. To address the challenge, we model the geometry, kinematics, and dynamics of non‐circular gears, formulate the design problem as a shape optimization, and identify necessary independent variables in the optimization search. Taking a pair of 2D shapes as inputs, our method optimizes them into gears by locating the rotation center on each shape, minimally modifying each shape to form the gear's boundary, and constructing appropriate teeth for gear meshing. Our optimized gears not only resemble the inputs but can also drive the motion with relatively small torque. We demonstrate our method's usability by generating a rich variety of non‐circular gears from various inputs and 3D printing several of them.

Shadow detection and shadow removal are fundamental and challenging tasks, requiring an understanding of the global image semantics. This paper presents a novel deep neural network design for shadow detection and removal by analyzing the spatial image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting and removing shadows. This design is developed into the DSC module and embedded in a convolutional neural network (CNN) to learn the DSC features at different levels. Moreover, we design a weighted cross entropy loss to make effective the training for shadow detection and further adopt the network for shadow removal by using a euclidean loss function and formulating a color transfer function to address the color and luminosity inconsistencies in the training pairs. We employed two shadow detection benchmark datasets and two shadow removal benchmark datasets, and performed various experiments to evaluate our method. Experimental results show that our method performs favorably against the state-of-the-art methods for both shadow detection and shadow removal.

This paper presents a novel deep learning model to aggregate the attentional dilated features for salient object detection by exploring the complementary information between the global and local context in a convolutional neural network. There are two technical contributions to our network design. First, we develop an attentional dense atrous (dilated) spatial pyramid pooling (AD-ASPP) module to selectively use the local saliency cues captured by dilated convolutions with a small rate and the global saliency cues captured by dilated convolutions with a large rate. Second, taking the feature pyramid network as the backbone, we develop an aggregation network to integrate the refined features by formulating two consecutive chains of residual learning based modules: one chain from deep to shallow layers while another chain from shallow to deep layers. We evaluate our network on seven widely-used saliency detection benchmarks by comparing it against 21 state-of-the-art methods. Experimental results show that our network outperforms others on all the seven benchmark datasets.

This paper presents a new approach to recognizing vanishing-point-constrained building planes from a single image of street view. We first design a novel convolutional neural network (CNN) architecture that generates geometric segmentation of per-pixel orientations from a single street-view image. The network combines two-stream features of general visual cues and surface normals in gated convolution layers, and employs a deeply supervised loss that encapsulates multi-scale convolutional features. Our experiments on a new benchmark with fine-grained plane segmentations of real-world street views show that our network outperforms state-of-the-arts methods of both semantic and geometric segmentation. The pixel-wise segmentation exhibits coarse boundaries and discontinuities. We then propose to rectify the pixel-wise segmentation into perspectively-projected quads based on spatial proximity between the segmentation masks and exterior line segments detected through an image processing. We demonstrate how the results can be utilized to perspectively overlay images and icons on building planes in input photos, and provide visual cues for various applications.

Diabetic retinopathy (DR) and diabetic macular edema (DME) are the leading causes of permanent blindness in the working-age population. Automatic grading of DR and DME helps ophthalmologists design tailored treatments to patients, thus is of vital importance in the clinical practice. However, prior works either grade DR or DME, and ignore the correlation between DR and its complication, i.e., DME. Moreover, the location information, e.g., macula and soft hard exhaust annotations, are widely used as a prior for grading. Such annotations are costly to obtain, hence it is desirable to develop automatic grading methods with only image-level supervision. In this article, we present a novel cross-disease attention network (CANet) to jointly grade DR and DME by exploring the internal relationship between the diseases with only image-level supervision. Our key contributions include the disease-specific attention module to selectively learn useful features for individual diseases, and the disease-dependent attention module to further capture the internal relationship between the two diseases. We integrate these two attention modules in a deep network to produce disease-specific and disease-dependent features, and to maximize the overall performance jointly for grading DR and DME. We evaluate our network on two public benchmark datasets, i.e., ISBI 2018 IDRiD challenge dataset and Messidor dataset. Our method achieves the best result on the ISBI 2018 IDRiD challenge dataset and outperforms other methods on the Messidor dataset. Our code is publicly available at https://github.com/xmengli999/CANet.

Sub-cortical brain structure segmentation is of great importance for diagnosing neuropsychiatric disorders. However, developing an automatic approach to segmenting sub-cortical brain structures remains very challenging due to the ambiguous boundaries, complex anatomical structures, and large variance of shapes. This paper presents a novel deep network architecture, namely Ψ -Net, for sub-cortical brain structure segmentation, aiming at selectively aggregating features and boosting the information propagation in a deep convolutional neural network (CNN). To achieve this, we first formulate a densely convolutional LSTM module (DC-LSTM) to selectively aggregate the convolutional features with the same spatial resolution at the same stage of a CNN. This helps to promote the discriminativeness of features at each CNN stage. Second, we stack multiple DC-LSTMs from the deepest stage to the shallowest stage to progressively enrich low-level feature maps with high-level context. We employ two benchmark datasets on sub-cortical brain structure segmentation, and perform various experiments to evaluate the proposed Ψ -Net. The experimental results show that our network performs favorably against the state-of-the-art methods on both benchmark datasets.

Deep convolutional neural networks have significantly boosted the performance of fundus image segmentation when test datasets have the same distribution as the training datasets. However, in clinical practice, medical images often exhibit variations in appearance for various reasons, e.g., different scanner vendors and image quality. These distribution discrepancies could lead the deep networks to over-fit on the training datasets and lack generalization ability on the unseen test datasets. To alleviate this issue, we present a novel Domain-oriented Feature Embedding (DoFE) framework to improve the generalization ability of CNNs on unseen target domains by exploring the knowledge from multiple source domains. Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains to make the semantic features more discriminative. Specifically, we introduce a Domain Knowledge Pool to learn and memorize the prior information extracted from multi-source domains. Then the original image features are augmented with domain-oriented aggregated features, which are induced from the knowledge pool based on the similarity between the input image and multi-source domain images. We further design a novel domain code prediction branch to infer this similarity and employ an attention-guided mechanism to dynamically combine the aggregated features with the semantic features. We comprehensively evaluate our DoFE framework on two fundus image segmentation tasks, including the optic cup and disc segmentation and vessel segmentation. Our DoFE framework generates satisfying segmentation results on unseen datasets and surpasses other domain generalization and network regularization methods.

This paper presents the idea of mono-nizing binocular videos and a framework to effectively realize it. Mono-nize means we purposely convert a binocular video into a regular monocular video with the stereo information implicitly encoded in a visual but nearly-imperceptible form. Hence, we can impartially distribute and show the mononized video as an ordinary monocular video. Unlike ordinary monocular videos, we can restore from it the original binocular video and show it on a stereoscopic display. To start, we formulate an encoding-and-decoding framework with the pyramidal deformable fusion module to exploit long-range correspondences between the left and right views, a quantization layer to suppress the restoring artifacts, and the compression noise simulation module to resist the compression noise introduced by modern video codecs. Our framework is self-supervised, as we articulate our objective function with loss terms defined on the input: a monocular term for creating the mononized video, an invertibility term for restoring the original video, and a temporal term for frame-to-frame coherence. Further, we conducted extensive experiments to evaluate our generated mononized videos and restored binocular videos for diverse types of images and 3D movies. Quantitative results on both standard metrics and user perception studies show the effectiveness of our method.

This article presents a novel approach to learn and detect distinctive regions on 3D shapes. Unlike previous works, which require labeled data, our method is unsupervised. We conduct the analysis on point sets sampled from 3D shapes, then formulate and train a deep neural network for an unsupervised shape clustering task to learn local and global features for distinguishing shapes with respect to a given shape set. To drive the network to learn in an unsupervised manner, we design a clustering-based nonparametric softmax classifier with an iterative re-clustering of shapes, and an adapted contrastive loss for enhancing the feature embedding quality and stabilizing the learning process. By then, we encourage the network to learn the point distinctiveness on the input shapes. We extensively evaluate various aspects of our approach and present its applications for distinctiveness-guided shape retrieval, sampling, and view selection in 3D scenes.

We introduce the first neural optimization framework to solve a classical instance of the tiling problem. Namely, we seek a non-periodic tiling of an arbitrary 2D shape using one or more types of tiles---the tiles maximally fill the shape's interior without overlaps or holes. To start, we reformulate tiling as a graph problem by modeling candidate tile locations in the target shape as graph nodes and connectivity between tile locations as edges. Further, we build a graph convolutional neural network , coined TilinGNN, to progressively propagate and aggregate features over graph edges and predict tile placements. TilinGNN is trained by maximizing the tiling coverage on target shapes, while avoiding overlaps and holes between the tiles. Importantly, our network is self-supervised , as we articulate these criteria as loss terms defined on the network outputs, without the need of ground-truth tiling solutions. After training, the runtime of TilinGNN is roughly linear to the number of candidate tile locations, significantly outperforming traditional combinatorial search. We conducted various experiments on a variety of shapes to showcase the speed and versatility of TilinGNN. We also present comparisons to alternative methods and manual solutions, robustness analysis, and ablation studies to demonstrate the quality of our approach.

We present a non-uniform recursive sampling technique for multi-class scatterplots, with the specific goal of faithfully presenting relative data and class densities, while preserving major outliers in the plots. Our technique is based on a customized binary kd-tree, in which leaf nodes are created by recursively subdividing the underlying multi-class density map. By backtracking, we merge leaf nodes until they encompass points of all classes for our subsequently applied outlier-aware multi-class sampling strategy. A quantitative evaluation shows that our approach can better preserve outliers and at the same time relative densities in multi-class scatterplots compared to the previous approaches, several case studies demonstrate the effectiveness of our approach in exploring complex and real world data.

Selection is a fundamental task in exploratory analysis and visualization of 3D point clouds. Prior researches on selection methods were developed mainly based on heuristics such as local point density, thus limiting their applicability in general data. Specific challenges root in the great variabilities implied by point clouds (e.g., dense vs. sparse), viewpoint (e.g., occluded vs. non-occluded), and lasso (e.g., small vs. large). In this work, we introduce LassoNet, a new deep neural network for lasso selection of 3D point clouds, attempting to learn a latent mapping from viewpoint and lasso to point cloud regions. To achieve this, we couple user-target points with viewpoint and lasso information through 3D coordinate transform and naive selection, and improve the method scalability via an intention filtering and farthest point sampling. A hierarchical network is trained using a dataset with over 30K lasso-selection records on two different point cloud data. We conduct a formal user study to compare LassoNet with two state-of-the-art lasso-selection methods. The evaluations confirm that our approach improves the selection effectiveness and efficiency across different combinations of 3D point clouds, viewpoints, and lasso selections. Project Website: https://LassoNet.github.io.

We present a new technique to enable the creation of shape-bounded Wordles, we call ShapeWordle, in which we fit words to form a given shape. To guide word placement within a shape, we extend the traditional Archimedean spirals to be shape-aware by formulating the spirals in a differential form using the distance field of the shape. To handle non-convex shapes, we introduce a multi-centric Wordle layout method that segments the shape into parts for our shape-aware spirals to adaptively fill the space and generate word placements. In addition, we offer a set of editing interactions to facilitate the creation of semantically-meaningful Wordles. Lastly, we present three evaluations: a comprehensive comparison of our results against the state-of-the-art technique (WordArt), case studies with 14 users, and a gallery to showcase the coverage of our technique.

Many edge bundling techniques (i.e., data simplification as a support for data visualization and decision making) exist but they are not directly applicable to any kind of dataset and their parameters are often too abstract and difficult to set up. As a result, this hinders the user ability to create efficient aggregated visualizations. To address these issues, we investigated a novel way of handling visual aggregation with a task-driven and user-centered approach. Given a graph, our approach produces a decluttered view as follows: first, the user investigates different edge bundling results and specifies areas, where certain edge bundling techniques would provide user-desired results. Second, our system then computes a smooth and structural preserving transition between these specified areas. Lastly, the user can further fine-tune the global visualization with a direct manipulation technique to remove the local ambiguity and to apply different visual deformations. In this paper, we provide details for our design rationale and implementation. Also, we show how our algorithm gives more suitable results compared to current edge bundling techniques, and in the end, we provide concrete instances of usages, where the algorithm combines various edge bundling results to support diverse data exploration and visualizations.

Texture smoothing aims to smooth out textures in images, while retaining the prominent structures. This paper presents a saliency-aware approach to the problem with two key contributions. First, we design a deep saliency network with guided non-local blocks (GNLBs) for learning long-range pixel dependencies by taking the predicted saliency map at former layer as the guidance image to help suppress the non-saliency regions in the shallow layer. The GNLB computes the saliency response at a position by a weighted sum of features at all positions, and enables us to produce results that outperform existing deep saliency models. Second, we formulate a joint optimization framework to take saliency information when iteratively separating textures from structures: on the texture layer, we smooth out structures with the help of the saliency information and migrate structures from the texture to structure layer, while on the structure layer, we adopt another deep model to detect edges and simultaneous sparse coding to push textures back to the texture layer. We tested our method on a rich variety of images and compared it with several state-of-the-art methods. Both visual and quantitative comparison results show that our method better preserves structures while removing the texture components.

Rain is a common weather phenomenon, where object visibility varies with depth from the camera and objects faraway are visually blocked more by fog than by rain streaks. Existing methods and datasets for rain removal, however, ignore these physical properties, thereby limiting the rain removal efficiency on real photos. In this work, we first analyze the visual effects of rain subject to scene depth and formulate a rain imaging model collectively with rain streaks and fog; by then, we prepare a new dataset called RainCityscapes with rain streaks and fog on real outdoor photos. Furthermore, we design an end-to-end deep neural network, where we train it to learn depth-attentional features via a depth-guided attention mechanism, and regress a residual map to produce the rain-free image output. We performed various experiments to visually and quantitatively compare our method with several state-of-the-art methods to demonstrate its superiority over the others.

This paper presents a new neural network for enhancing underexposed photos. Instead of directly learning an image-to-image mapping as previous work, we introduce intermediate illumination in our network to associate the input with expected enhancement result, which augments the network's capability to learn complex photographic adjustment from expert-retouched input/output image pairs. Based on this model, we formulate a loss function that adopts constraints and priors on the illumination, prepare a new dataset of 3,000 underexposed image pairs, and train the network to effectively learn a rich variety of adjustment for diverse lighting conditions. By these means, our network is able to recover clear details, distinct contrast, and natural color in the enhancement results. We perform extensive experiments on the benchmark MIT-Adobe FiveK dataset and our new dataset, and show that our network is effective to deal with previously challenging images.

This paper presents PointWeb, a new approach to extract contextual features from local neighborhood in a point cloud. Unlike previous work, we densely connect each point with every other in a local neighborhood, aiming to specify feature of each point based on the local region characteristics for better representing the region. A novel module, namely Adaptive Feature Adjustment (AFA) module, is presented to find the interaction between points. For each local region, an impact map carrying element-wise impact between point pairs is applied to the feature difference map. Each feature is then pulled or pushed by other features in the same region according to the adaptively learned impact indicators. The adjusted features are well encoded with region information, and thus benefit the point cloud recognition tasks, such as point cloud segmentation and classification. Experimental results show that our model outperforms the state-of-the-arts on both semantic segmentation and shape classification datasets.

This paper presents a deep multi-model fusion network to attentively integrate multiple models to separate layers and boost the performance in single-image dehazing. To do so, we first formulate the attentional feature integration module to maximize the integration of the convolutional neural network (CNN) features at different CNN layers and generate the attentional multi-level integrated features (AMLIF). Then, from the AMLIF, we further predict a haze-free result for an atmospheric scattering model, as well as for four haze-layer separation models, and then fuse the results together to produce the final haze-free image. To evaluate the effectiveness of our method, we compare our network with several state-of-the-art methods on two widely-used dehazing benchmark datasets, as well as on two sets of real-world hazy images. Experimental results demonstrate clear quantitative and qualitative improvements of our method over the state-of-the-arts.

This paper presents a new method for shadow removal using unpaired data, enabling us to avoid tedious annotations and obtain more diverse training samples. However, directly employing adversarial learning and cycle-consistency constraints is insufficient to learn the underlying relationship between the shadow and shadow-free domains, since the mapping between shadow and shadow-free images is not simply one-to-one. To address the problem, we formulate Mask-ShadowGAN, a new deep framework that automatically learns to produce a shadow mask from the input shadow image and then takes the mask to guide the shadow generation via re-formulated cycle-consistency constraints. Particularly, the framework simultaneously learns to produce shadow masks and learns to remove shadows, to maximize the overall performance. Also, we prepared an unpaired dataset for shadow removal and demonstrated the effectiveness of Mask-ShadowGAN on various experiments, even it was trained on unpaired data.

We achieve 3D semantic scene labeling by exploring semantic relation between each point and its contextual neighbors through edges. Besides an encoder-decoder branch for predicting point labels, we construct an edge branch to hierarchically integrate point features and generate edge features. To incorporate point features in the edge branch, we establish a hierarchical graph framework, where the graph is initialized from a coarse layer and gradually enriched along the point decoding process. For each edge in the final graph, we predict a label to indicate the semantic consistency of the two connected points to enhance point prediction. At different layers, edge features are also fed into the corresponding point module to integrate contextual information for message passing enhancement in local regions. The two branches interact with each other and cooperate in segmentation. Decent experimental results on several 3D semantic labeling datasets demonstrate the effectiveness of our work.

Point clouds acquired from range scans are often sparse, noisy, and non-uniform. This paper presents a new point cloud upsampling network called PU-GAN1, which is formulated based on a generative adversarial network (GAN), to learn a rich variety of point distributions from the latent space and upsample points over patches on object surfaces. To realize a working GAN network, we construct an up-down-up expansion unit in the generator for upsampling point features with error feedback and self-correction, and formulate a self-attention unit to enhance the feature integration. Further, we design a compound loss with adversarial, uniform and reconstruction terms, to encourage the discriminator to learn more latent patterns and enhance the output point distribution uniformity. Qualitative and quantitative evaluations demonstrate the quality of our results over the state-of-the-arts in terms of distribution uniformity, proximity-to-surface, and 3D reconstruction quality.

This paper presents a new approach to recognize elements in floor plan layouts. Besides walls and rooms, we aim to recognize diverse floor plan elements, such as doors, windows and different types of rooms, in the floor layouts. To this end, we model a hierarchy of floor plan elements and design a deep multi-task neural network with two tasks: one to learn to predict room-boundary elements, and the other to predict rooms with types. More importantly, we formulate the room-boundary-guided attention mechanism in our spatial contextual module to carefully take room-boundary features into account to enhance the room-type predictions. Furthermore, we design a cross-and-within-task weighted loss to balance the multi-label tasks and prepare two new datasets for floor plan recognition. Experimental results demonstrate the superiority and effectiveness of our network over the state-of-the-art methods.

Abstract Turbulent flows are multi‐scale with vortices spanning a wide range of scales continuously. Due to such complexities, turbulence scales are particularly difficult to analyse and visualize. In this work, we present a novel and efficient optimization‐based method for continuous‐scale turbulence structure visualization with scale decomposition directly in the Kolmogorov energy spectrum. To achieve this, we first derive a new analytical objective function based on integration approximation. Using this new formulation, we can significantly improve the efficiency of the underlying optimization process and obtain the desired filter in the Kolmogorov energy spectrum for scale decomposition. More importantly, such a decomposition allows a ‘continuous‐scale visualization’ that enables us to efficiently explore the decomposed turbulence scales and further analyse the turbulence structures in a continuous manner. With our approach, we can present scale visualizations of direct numerical simulation data sets continuously over the scale domain for both isotropic and boundary layer turbulent flows. Compared with previous works on multi‐scale turbulence analysis and visualization, our method is highly flexible and efficient in generating scale decomposition and visualization results. The application of the proposed technique to both isotropic and boundary layer turbulence data sets verifies the capability of our technique to produce desirable scale visualization results.

Abstract Dissection puzzles require assembling a common set of pieces into multiple distinct forms. Existing works focus on creating 2D dissection puzzles that form primitive or naturalistic shapes. Unlike 2D dissection puzzles that could be supported on a tabletop surface, 3D dissection puzzles are preferable to be steady by themselves for each assembly form. In this work, we aim at computationally designing steady 3D dissection puzzles. We address this challenging problem with three key contributions. First, we take two voxelized shapes as inputs and dissect them into a common set of puzzle pieces, during which we allow slightly modifying the input shapes, preferably on their internal volume, to preserve the external appearance. Second, we formulate a formal model of generalized interlocking for connecting pieces into a steady assembly using both their geometric arrangements and friction. Third, we modify the geometry of each dissected puzzle piece based on the formal model such that each assembly form is steady accordingly. We demonstrate the effectiveness of our approach on a wide variety of shapes, compare it with the state‐of‐the‐art on 2D and 3D examples, and fabricate some of our designed puzzles to validate their steadiness.

Glaucoma is a leading cause of irreversible blindness. Accurate segmentation of the optic disc (OD) and optic cup (OC) from fundus images is beneficial to glaucoma screening and diagnosis. Recently, convolutional neural networks demonstrate promising progress in the joint OD and OC segmentation. However, affected by the domain shift among different datasets, deep networks are severely hindered in generalizing across different scanners and institutions. In this paper, we present a novel patch-based output space adversarial learning framework ( p OSAL) to jointly and robustly segment the OD and OC from different fundus image datasets. We first devise a lightweight and efficient segmentation network as a backbone. Considering the specific morphology of OD and OC, a novel morphology-aware segmentation loss is proposed to guide the network to generate accurate and smooth segmentation. Our p OSAL framework then exploits unsupervised domain adaptation to address the domain shift challenge by encouraging the segmentation in the target domain to be similar to the source ones. Since the whole-segmentation-based adversarial loss is insufficient to drive the network to capture segmentation details, we further design the p OSAL in a patch-based fashion to enable fine-grained discrimination on local segmentation details. We extensively evaluate our p OSAL framework and demonstrate its effectiveness in improving the segmentation performance on three public retinal fundus image datasets, i.e., Drishti-GS, RIM-ONE-r3, and REFUGE. Furthermore, our p OSAL framework achieved the first place in the OD and OC segmentation tasks in the MICCAI 2018 Retinal Fundus Glaucoma Challenge.

research-article Computational LEGO technic design Share on Authors: Hao Xu View Profile , Ka-Hei Hui View Profile , Chi-Wing Fu View Profile , Hao Zhang View Profile Authors Info & Claims ACM Transactions on GraphicsVolume 38Issue 6December 2019 Article No.: 196https://doi.org/10.1145/3355089.3356504Online:27 August 2021Publication History 6citation11DownloadsMetricsTotal Citations6Total Downloads11Last 12 Months11Last 6 weeks4 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Appropriate choice of colors significantly aids viewers in understanding the structures in multiclass scatterplots and becomes more important with a growing number of data points and groups. An appropriate color mapping is also an important parameter for the creation of an aesthetically pleasing scatterplot. Currently, users of visualization software routinely rely on color mappings that have been pre-defined by the software. A default color mapping, however, cannot ensure an optimal perceptual separability between groups, and sometimes may even lead to a misinterpretation of the data. In this paper, we present an effective approach for color assignment based on a set of given colors that is designed to optimize the perception of scatterplots. Our approach takes into account the spatial relationships, density, degree of overlap between point clusters, and also the background color. For this purpose, we use a genetic algorithm that is able to efficiently find good color assignments. We implemented an interactive color assignment system with three extensions of the basic method that incorporates top K suggestions, user-defined color subsets, and classes of interest for the optimization. To demonstrate the effectiveness of our assignment technique, we conducted a numerical study and a controlled user study to compare our approach with default color assignments; our findings were verified by two expert studies. The results show that our approach is able to support users in distinguishing cluster numbers faster and more precisely than default assignment methods.

Selecting a good aspect ratio is crucial for effective 2D diagrams. There are several aspect ratio selection methods for function plots and line charts, but only few can handle general, discrete diagrams such as 2D scatter plots. However, these methods either lack a perceptual foundation or heavily rely on intermediate isoline representations, which depend on choosing the right isovalues and are time-consuming to compute. This paper introduces a general image-based approach for selecting aspect ratios for a wide variety of 2D diagrams, ranging from scatter plots and density function plots to line charts. Our approach is derived from Federer's co-area formula and a line integral representation that enable us to directly construct image-based versions of existing selection methods using density fields. In contrast to previous methods, our approach bypasses isoline computation, so it is faster to compute, while following the perceptual foundation to select aspect ratios. Furthermore, this approach is complemented by an anisotropic kernel density estimation to construct density fields, allowing us to more faithfully characterize data patterns, such as the subgroups in scatterplots or dense regions in time series. We demonstrate the effectiveness of our approach by quantitatively comparing to previous methods and revisiting a prior user study. Finally, we present extensions for ROI banking, multi-scale banking, and the application to image data.

Traditional fisheye views for exploring large graphs introduce substantial distortions that often lead to a decreased readability of paths and other interesting structures. To overcome these problems, we propose a framework for structure-aware fisheye views. Using edge orientations as constraints for graph layout optimization allows us not only to reduce spatial and temporal distortions during fisheye zooms, but also to improve the readability of the graph structure. Furthermore, the framework enables us to optimize fisheye lenses towards specific tasks and design a family of new lenses: polyfocal, cluster, and path lenses. A GPU implementation lets us process large graphs with up to 15,000 nodes at interactive rates. A comprehensive evaluation, a user study, and two case studies demonstrate that our structure-aware fisheye views improve layout readability and user performance.

Salient object detection is a fundamental yet challenging problem in computer vision, aiming to highlight the most visually distinctive objects or regions in an image. Recent works benefit from the development of fully convolutional neural networks (FCNs) and achieve great success by integrating features from multiple layers of FCNs. However, the integrated features tend to include non-salient regions (due to low level features of the FCN) or lost details of salient objects (due to high level features of the FCN) when producing the saliency maps. In this paper, we develop a novel deep saliency network equipped with recurrently aggregated deep features (RADF) to more accurately detect salient objects from an image by fully exploiting the complementary saliency information captured in different layers. The RADF utilizes the multi-level features integrated from different layers of a FCN to recurrently refine the features at each layer, suppressing the non-salient noise at low-level of the FCN and increasing more salient details into features at high layers. We perform experiments to evaluate the effectiveness of the proposed network on 5 famous saliency detection benchmarks and compare it with 15 state-of-the-art methods. Our method ranks first in 4 of the 5 datasets and second in the left dataset.

Shadow detection is a fundamental and challenging task, since it requires an understanding of global image semantics and there are various backgrounds around shadows. This paper presents a novel network for shadow detection by analyzing image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting shadows. This design is developed into the DSC module and embedded in a CNN to learn DSC features at different levels. Moreover, a weighted cross entropy loss is designed to make the training more effective. We employ two common shadow detection benchmark datasets and perform various experiments to evaluate our network. Experimental results show that our network outperforms state-of-the-art methods and achieves 97% accuracy and 38% reduction on balance error rate.

Learning and analyzing 3D point clouds with deep networks is challenging due to the sparseness and irregularity of the data. In this paper, we present a data-driven point cloud upsampling technique. The key idea is to learn multi-level features per point and expand the point set via a multi-branch convolution unit implicitly in feature space. The expanded feature is then split to a multitude of features, which are then reconstructed to an upsampled point set. Our network is applied at a patch-level, with a joint loss function that encourages the upsampled points to remain on the underlying surface with a uniform distribution. We conduct various experiments using synthesis and scan data to evaluate our method and demonstrate its superiority over some baseline methods and an optimization-based method. Results show that our upsampled points have better uniformity and are located closer to the underlying surfaces.

Abstract This paper presents a non‐local low‐rank normal filtering method for mesh denoising. By exploring the geometric similarity between local surface patches on 3D meshes in the form of normal fields, we devise a low‐rank recovery model that filters normal vectors by means of patch groups. In summary, our method has the following key contributions. First, we present the guided normal patch covariance descriptor to analyze the similarity between patches. Second, we pack normal vectors on similar patches into the normal‐field patch‐group (NPG) matrix for rank analysis. Third, we formulate mesh denoising as a low‐rank matrix recovery problem based on the prior that the rank of the NPG matrix is high for raw meshes with noise, but can be significantly reduced for denoised meshes, whose normal vectors across similar patches should be more strongly correlated. Furthermore, we devise an objective function based on an improved truncated γ norm, and derive an op tim ization procedure using the alternative direction method of multipliers and iteratively re‐weighted least squares techniques. We conducted several experiments to evaluate our method using various 3D models, and compared our results against several state‐of‐the‐art methods. Experimental results show that our method consistently outperforms other methods and better preserves the fine details.

We propose an analysis of surgical videos that is based on a novel recurrent convolutional network (SV-RCNet), specifically for automatic workflow recognition from surgical videos online, which is a key component for developing the context-aware computer-assisted intervention systems. Different from previous methods which harness visual and temporal information separately, the proposed SV-RCNet seamlessly integrates a convolutional neural network (CNN) and a recurrent neural network (RNN) to form a novel recurrent convolutional architecture in order to take full advantages of the complementary information of visual and temporal features learned from surgical videos. We effectively train the SV-RCNet in an end-to-end manner so that the visual representations and sequential dynamics can be jointly optimized in the learning process. In order to produce more discriminative spatio-temporal features, we exploit a deep residual network (ResNet) and a long short term memory (LSTM) network, to extract visual features and temporal dependencies, respectively, and integrate them into the SV-RCNet. Moreover, based on the phase transition-sensitive predictions from the SV-RCNet, we propose a simple yet effective inference scheme, namely the prior knowledge inference (PKI), by leveraging the natural characteristic of surgical video. Such a strategy further improves the consistency of results and largely boosts the recognition performance. Extensive experiments have been conducted with the MICCAI 2016 Modeling and Monitoring of Computer Assisted Interventions Workflow Challenge dataset and Cholec80 dataset to validate SV-RCNet. Our approach not only achieves superior performance on these two datasets but also outperforms the state-of-the-art methods by a significant margin.

Liver cancer is one of the leading causes of cancer death. To assist doctors in hepatocellular carcinoma diagnosis and treatment planning, an accurate and automatic liver and tumor segmentation method is highly demanded in the clinical practice. Recently, fully convolutional neural networks (FCNs), including 2-D and 3-D FCNs, serve as the backbone in many volumetric image segmentation. However, 2-D convolutions cannot fully leverage the spatial information along the third dimension while 3-D convolutions suffer from high computational cost and GPU memory consumption. To address these issues, we propose a novel hybrid densely connected UNet (H-DenseUNet), which consists of a 2-D DenseUNet for efficiently extracting intra-slice features and a 3-D counterpart for hierarchically aggregating volumetric contexts under the spirit of the auto-context algorithm for liver and tumor segmentation. We formulate the learning process of the H-DenseUNet in an end-to-end manner, where the intra-slice representations and inter-slice features can be jointly optimized through a hybrid feature fusion layer. We extensively evaluated our method on the data set of the MICCAI 2017 Liver Tumor Segmentation Challenge and 3DIRCADb data set. Our method outperformed other state-of-the-arts on the segmentation results of tumors and achieved very competitive performance for liver segmentation even with a single model.

We introduce a computational solution for cost-efficient 3D fabrication using universal building blocks. Our key idea is to employ a set of universal blocks, which can be massively prefabricated at a low cost, to quickly assemble and constitute a significant internal core of the target object, so that only the residual volume need to be 3D printed online. We further improve the fabrication efficiency by decomposing the residual volume into a small number of printing-friendly pyramidal pieces. Computationally, we face a coupled decomposition problem: decomposing the input object into an internal core and residual, and decomposing the residual, to fulfill a combination of objectives for efficient 3D fabrication. To this end, we formulate an optimization that jointly minimizes the residual volume, the number of pyramidal residual pieces, and the amount of support waste when printing the residual pieces. To solve the optimization in a tractable manner, we start with a maximal internal core and iteratively refine it with local cuts to minimize the cost function. Moreover, to efficiently explore the large search space, we resort to cost estimates aided by pre-computation and avoid the need to explicitly construct pyramidal decompositions for each solution candidate. Results show that our method can iteratively reduce the estimated printing time and cost, as well as the support waste, and helps to save hours of fabrication time and much material consumption.

We present a fully automatic method that finds a small number of machine fabricable wires with minimal overlap to reproduce a wire sculpture design as a 3D shape abstraction. Importantly, we consider non-planar wires, which can be fabricated by a wire bending machine, to enable efficient construction of complex 3D sculptures that cannot be achieved by previous works. We call our wires Eulerian wires , since they are as Eulerian as possible with small overlap to form the target design together. Finding such Eulerian wires is highly challenging, due to an enormous search space. After exploring a variety of optimization strategies, we formulate a population-based hybrid metaheuristic model, and design the join, bridge and split operators to refine the solution wire sets in the population. We start the exploration of each solution wire set in a bottom-up manner, and adopt an adaptive simulated annealing model to regulate the exploration. By further formulating a meta model on top to optimize the cooling schedule, and precomputing fabricable subwires, our method can efficiently find promising solutions with low wire count and overlap in one to two minutes. We demonstrate the efficiency of our method on a rich variety of wire sculptures, and physically fabricate several of them. Our results show clear improvements over other optimization alternatives in terms of solution quality, versatility, and scalability.

Superfluidity is a special state of matter exhibiting macroscopic quantum phenomena and acting like a fluid with zero viscosity. In such a state, superfluid vortices exist as phase singularities of the model equation with unique distributions. This paper presents novel techniques to aid the visual understanding of superfluid vortices based on the state-of-the-art non-linear Klein-Gordon equation, which evolves a complex scalar field, giving rise to special vortex lattice/ring structures with dynamic vortex formation, reconnection, and Kelvin waves, etc. By formulating a numerical model with theoretical physicists in superfluid research, we obtain high-quality superfluid flow data sets without noise-like waves, suitable for vortex visualization. By further exploring superfluid vortex properties, we develop a new vortex identification and visualization method: a novel mechanism with velocity circulation to overcome phase singularity and an orthogonal-plane strategy to avoid ambiguity. Hence, our visualizations can help reveal various superfluid vortex structures and enable domain experts for related visual analysis, such as the steady vortex lattice/ring structures, dynamic vortex string interactions with reconnections and energy radiations, where the famous Kelvin waves and decaying vortex tangle were clearly observed. These visualizations have assisted physicists to verify the superfluid model, and further explore its dynamic behavior more intuitively.

Shading is a tedious process for artists involved in 2D cartoon and manga production given the volume of contents that the artists have to prepare regularly over tight schedule. While we can automate shading production with the presence of geometry, it is impractical for artists to model the geometry for every single drawing. In this work, we aim to automate shading generation by analyzing the local shapes, connections, and spatial arrangement of wrinkle strokes in a clean line drawing. By this, artists can focus more on the design rather than the tedious manual editing work, and experiment with different shading effects under different conditions. To achieve this, we have made three key technical contributions. First, we model five perceptual cues by exploring relevant psychological principles to estimate the local depth profile around strokes. Second, we formulate stroke interpretation as a global optimization model that simultaneously balances different interpretations suggested by the perceptual cues and minimizes the interpretation discrepancy. Lastly, we develop a wrinkle-aware inflation method to generate a height field for the surface to support the shading region computation. In particular, we enable the generation of two commonly-used shading styles: 3D-like soft shading and manga-style flat shading.

Dimensionality reduction (DR) is a common strategy for visual analysis of labeled high-dimensional data. Low-dimensional representations of the data help, for instance, to explore the class separability and the spatial distribution of the data. Widely-used unsupervised DR methods like PCA do not aim to maximize the class separation, while supervised DR methods like LDA often assume certain spatial distributions and do not take perceptual capabilities of humans into account. These issues make them ineffective for complicated class structures. Towards filling this gap, we present a perception-driven linear dimensionality reduction approach that maximizes the perceived class separation in projections. Our approach builds on recent developments in perception-based separation measures that have achieved good results in imitating human perception. We extend these measures to be density-aware and incorporate them into a customized simulated annealing algorithm, which can rapidly generate a near optimal DR projection. We demonstrate the effectiveness of our approach by comparing it to state-of-the-art DR methods on 93 datasets, using both quantitative measure and human judgments. We also provide case studies with class-imbalanced and unlabeled data.

We present an improved stress majorization method that incorporates various constraints, including directional constraints without the necessity of solving a constraint optimization problem. This is achieved by reformulating the stress function to impose constraints on both the edge vectors and lengths instead of just on the edge lengths (node distances). This is a unified framework for both constrained and unconstrained graph visualizations, where we can model most existing layout constraints, as well as develop new ones such as the star shapes and cluster separation constraints within stress majorization. This improvement also allows us to parallelize computation with an efficient GPU conjugant gradient solver, which yields fast and stable solutions, even for large graphs. As a result, we allow the constraint-based exploration of large graphs with 10K nodes - an approach which previous methods cannot support.

The aspect ratio of a line chart heavily influences the perception of the underlying data. Different methods explore different criteria in choosing aspect ratios, but so far, it was still unclear how to select aspect ratios appropriately for any given data. This paper provides a guideline for the user to choose aspect ratios for any input 1D curves by conducting an in-depth analysis of aspect ratio selection methods both theoretically and experimentally. By formulating several existing methods as line integrals, we explain their parameterization invariance. Moreover, we derive a new and improved aspect ratio selection method, namely the -LOR (local orientation resolution), with a certain degree of parameterization invariance. Furthermore, we connect different methods, including AL (arc length based method), the banking to 45 principle, RV (resultant vector) and AS (average absolute slope), as well as -LOR and AO (average absolute orientation). We verify these connections by a comparative evaluation involving various data sets, and show that the selections by RV and -LOR are complementary to each other for most data. Accordingly, we propose the dual-scale banking technique that combines the strengths of RV and -LOR, and demonstrate its practicability using multiple real-world data sets.

Speckle refers to the granular patterns that occur in ultrasound images due to wave interference. Speckle removal can greatly improve the visibility of the underlying structures in an ultrasound image and enhance subsequent post processing. We present a novel framework for speckle removal based on low-rank non-local filtering. Our approach works by first computing a guidance image that assists in the selection of candidate patches for non-local filtering in the face of significant speckles. The candidate patches are further refined using a low-rank minimization estimated using a truncated weighted nuclear norm (TWNN) and structured sparsity. We show that the proposed filtering framework produces results that outperform state-of-the-art methods both qualitatively and quantitatively. This framework also provides better segmentation results when used for pre-processing ultrasound images.

We present a novel method for removing rain streaks from a single input image by decomposing it into a rain-free background layer B and a rain-streak layer R. A joint optimization process is used that alternates between removing rain-streak details from B and removing non-streak details from R. The process is assisted by three novel image priors. Observing that rain streaks typically span a narrow range of directions, we first analyze the local gradient statistics in the rain image to identify image regions that are dominated by rain streaks. From these regions, we estimate the dominant rain streak direction and extract a collection of rain-dominated patches. Next, we define two priors on the background layer B, one based on a centralized sparse representation and another based on the estimated rain direction. A third prior is defined on the rain-streak layer R, based on similarity of patches to the extracted rain patches. Both visual and quantitative comparisons demonstrate that our method outperforms the state-of-the-art.

This paper presents FaceCollage, a robust and real-time system for head reconstruction that can be used to create easy-to-deploy telepresence systems, using a pair of consumer-grade RGBD cameras that provide a wide range of views of the reconstructed user. A key feature is that the system is very simple to rapidly deploy, with autonomous calibration and requiring minimal intervention from the user, other than casually placing the cameras. This system is realized through three technical contributions: (1) a fully automatic calibration method, which analyzes and correlates the left and right RGBD faces just by the face features; (2) an implementation that exploits the parallel computation capability of GPU throughout most of the system pipeline, in order to attain real-time performance; and (3) a complete integrated system on which we conducted various experiments to demonstrate its capability, robustness, and performance, including testing the system on twelve participants with visually-pleasing results.

In transportation studies, one fundamental problem is to analyze the departures and arrivals at locations in order to predict the travel demands for urban planning and traffic management. These movements can relate to many factors, e.g., activity distributions and household demographics. This paper presents how we use visualization to explore the relationship between people movements and activity distributions that are characterized by the points of interest (POIs). To effectively model and visualize such relationship, we introduce POI-mobility signature, a compact visual representation with two main components. 1) A mobility component to present major people movements information across temporal dimension. 2) A POI component to present the activity context over an area of interest in spatial domain. To derive the signature, we study assorted analytical tasks after discussing with transportation researchers, consider essential design principles, and apply the representation to study a real-world dataset, which is the massive public transportation data in Singapore with over 30 million trajectories and crowd-sourcing POIs retrieved from Foursquare. Finally, we conduct three case studies and interview three transportation experts to verify the efficacy of our method.

Reconfigurable assemblies consist of a common set of parts that can be assembled into different forms for use in different situations. Designing these assemblies is a complex problem, since it requires a compatible decomposition of shapes with correspondence across forms, and a planning of well-matched joints to connect parts in each form. This paper presents computational methods as tools to assist the design and construction of reconfigurable assemblies, typically for furniture. There are three key contributions in this work. First, we present the compatible decomposition as a weakly-constrained dissection problem, and derive its solution based on a dynamic bipartite graph to construct parts across multiple forms; particularly, we optimize the parts reuse and preserve the geometric semantics. Second, we develop a joint connection graph to model the solution space of reconfigurable assemblies with part and joint compatibility across different forms. Third, we formulate the backward interlocking and multi-key interlocking models, with which we iteratively plan the joints consistently over multiple forms. We show the applicability of our approach by constructing reconfigurable furniture of various complexities, extend it with recursive connections to generate extensible and hierarchical structures, and fabricate a number of results using 3D printing, 2D laser cutting, and woodworking.

Wind-up toys are mechanical assemblies that perform intriguing motions driven by a simple spring motor. Due to the limited motor force and small body size, wind-up toys often employ higher pair joints of less frictional contacts and connector parts of nontrivial shapes to transfer motions. These unique characteristics make them hard to design and fabricate as compared to other automata. This paper presents a computational system to aid the design of wind-up toys, focusing on constructing a compact internal wind-up mechanism to realize user-requested part motions. Our key contributions include an analytical modeling of a wide variety of elemental mechanisms found in common wind-up toys, including their geometry and kinematics, conceptual design of wind-up mechanisms by computing motion transfer trees to realize the requested part motions, automatic construction of wind-up mechanisms by connecting multiple elemental mechanisms, and an optimization on the part and joint geometry with an objective of compacting the mechanism, reducing its weight, and avoiding collision. We use our system to design wind-up toys of various forms, fabricate a number of them using 3D printing, and show the functionality of various results.

We introduce an interactive user-driven method to reconstruct high-relief 3D geometry from a single photo. Particularly, we consider two novel but challenging reconstruction issues: i) common non-rigid objects whose shapes are organic rather than polyhedral/symmetric, and ii) double-sided structures, where front and back sides of some curvy object parts are revealed simultaneously on image. To address these issues, we develop a three-stage computational pipeline. First, we construct a 2.5D model from the input image by user-driven segmentation, automatic layering, and region completion, handling three common types of occlusion. Second, users can interactively mark-up slope and curvature cues on the image to guide our constrained optimization model to inflate and lift up the image layers. We provide real-time preview of the inflated geometry to allow interactive editing. Third, we stitch and optimize the inflated layers to produce a high-relief 3D model. Compared to previous work, we can generate high-relief geometry with large viewing angles, handle complex organic objects with multiple occluded regions and varying shape profiles, and reconstruct objects with double-sided structures. Lastly, we demonstrate the applicability of our method on a wide variety of input images with human, animals, flowers, etc.

Human’s daily movements exhibit high regularity in a space–time context that typically forms circadian rhythms. Understanding the rhythms for human daily movements is of high interest to a variety of parties from urban planners, transportation analysts, to business strategists. In this paper, we present an interactive visual analytics design for understanding and utilizing data collected from tracking human’s movements. The resulting system identifies and visually presents frequent human movement rhythms to support interactive exploration and analysis of the data over space and time. Case studies using real-world human movement data, including massive urban public transportation data in Singapore and the MIT reality mining dataset, and interviews with transportation researches were conducted to demonstrate the effectiveness and usefulness of our system.

DIY cardboard-based VR headset that enfolds a commodity smartphone is a popular means of achieving low cost immersive stereoscopic viewing experiences. However, existing applications for these devices have limited user-input capability, allowing mainly look-at control by head tilting. CardboardSense is a set of novel tap-gesture-based inputs that take advantage of the motion sensing capabilities already available in most smartphones. The key premise is that finger contacts with the cardboard surface produce incidental but detectable vibrations that can be reliably differentiated from typical user head motion. Moreover, tapping on different surface locations produces differentiable temporal signatures in the sensor signals. We present methods to extract and analyze these temporal patterns, and experimentally determine a set of tapping gestures that can be accurately recognized. Experimental results show promising potential for CardboardSense to extend the interactivity of future cardboard-based VR headset applications.

Abstract Origin‐destination (OD) pattern is a highly useful means for transportation research since it summarizes urban dynamics and human mobility. However, existing visual analytics are insufficient for certain OD analytical tasks needed in transport research. For example, transport researchers are interested in path‐related movements across congested roads, besides global patterns over the entire domain. Driven by this need, we proposewaypoints‐constrained OD visual analytics, a new approach for exploring path‐related OD patterns in an urban transportation network. First, we use hashing‐based query to support interactive filtering of trajectories through user‐specified waypoints. Second, we elaborate a set of design principles and rules, and derive a novel unified visual representation called thewaypoints‐constrained OD viewby carefully considering the OD flow presentation, the temporal variation, spatial layout and user interaction. Finally, we demonstrate the effectiveness of our interface with two case studies and expert interviews with five transportation experts.

Abstract This paper presents a new image smoothing method that better preserves prominent structures. Our method is inspired by the recent non‐local image processing techniques on the patch grouping and filtering. Overall, it has three major contributions over previous works. First, we employ the diffusion map as the guidance image to improve the accuracy of patch similarity estimation using the region covariance descriptor. Second, we model structure‐preserving image smoothing as a low‐rank matrix recovery problem, aiming at effectively filtering the texture information in similar patches. Lastly, we devise an objective function, namely the weighted robust principle component analysis (WRPCA), by regularizing the low rank with the weighted nuclear norm and sparsity pursuit with L1norm, and solve this non‐convex WRPCA optimization problem by adopting the alternative direction method of multipliers (ADMM) technique. We experiment our method with a wide variety of images and compare it against several state‐of‐the‐art methods. The results show that our method achieves better structure preservation and texture suppression as compared to other methods. We also show the applicability of our method on several image processing tasks such as edge detection, texture enhancement and seam carving.

This paper tackles a challenging 2D collage generation problem, focusing on shapes: we aim to fill a given region by packing irregular and reasonably-sized shapes with minimized gaps and overlaps. To achieve this nontrivial problem, we first have to analyze the boundary of individual shapes and then couple the shapes with partially-matched boundary to reduce gaps and overlaps in the collages. Second, the search space in identifying a good coupling of shapes is highly enormous, since arranging a shape in a collage involves a position, an orientation, and a scale factor. Yet, this matching step needs to be performed for every single shape when we pack it into a collage. Existing shape descriptors are simply infeasible for computation in a reasonable amount of time. To overcome this, we present a brand new, scale- and rotation-invariant 2D shape descriptor, namely pyramid of arclength descriptor (PAD). Its formulation is locally supported, scalable, and yet simple to construct and compute. These properties make PAD efficient for performing the partial-shape matching. Hence, we can prune away most search space with simple calculation, and efficiently identify candidate shapes. We evaluate our method using a large variety of shapes with different types and contours. Convincing collage results in terms of visual quality and time performance are obtained.

This paper presents CofiFab, a coarse-to-fine 3D fabrication solution, combining 3D printing and 2D laser cutting for cost-effective fabrication of large objects at lower cost and higher speed. Our key approach is to first build coarse internal base structures within the given 3D object using laser cutting, and then attach thin 3D-printed parts, as an external shell, onto the base to recover the fine surface details. CofiFab achieves this with three novel algorithmic components. First, we formulate an optimization model to compute fabricatable polyhedrons of maximized volume, as the geometry of the internal base. Second, we devise a new interlocking scheme to tightly connect the laser-cut parts into a strong internal base, by iteratively building a network of nonorthogonal joints and interlocking parts around polyhedral corners. Lastly, we optimize the partitioning of the external object shell into 3D-printable parts, while saving support material and avoiding overhangs. Besides cost saving, these components also consider aesthetics, stability and balancing. Hence, CofiFab can efficiently produce large objects by assembly. To evaluate CofiFab, we fabricate objects of varying shapes and sizes, and show that CofiFab can significantly outperform previous methods.

Previous research on impossible figures focuses extensively on single view modeling and rendering. Existing computer games that employ impossible figures as navigation maze for gaming either use a fixed third-person view with axonometric projection to retain the figure's impossibility perception, or simply break the figure's impossibility upon view changes. In this paper, we present a new approach towards 3D gaming with impossible figures, delivering for the first time navigation in 3D mazes constructed from impossible figures. Such result cannot be achieved by previous research work in modeling impossible figures. To deliver seamless gaming navigation and interaction, we propose i) a set of guiding principles for bringing out subtle perceptions and ii) a novel computational approach to construct 3D structures from impossible figure images and then to dynamically construct the impossible-figure maze subjected to user's view. In the end, we demonstrate and discuss our method with a variety of generic maze types.

This paper presents a variational algorithm for feature-preserved mesh denoising. At the heart of the algorithm is a novel variational model composed of three components: fidelity, regularization and fairness, which are specifically designed to have their intuitive roles. In particular, the fidelity is formulated as an L1 data term, which makes the regularization process be less dependent on the exact value of outliers and noise. The regularization is formulated as the total absolute edge-lengthed supplementary angle of the dihedral angle, making the model capable of reconstructing meshes with sharp features. In addition, an augmented Lagrange method is provided to efficiently solve the proposed variational model. Compared to the prior art, the new algorithm has crucial advantages in handling large scale noise, noise along random directions, and different kinds of noise, including random impulsive noise, even in the presence of sharp features. Both visual and quantitative evaluation demonstrates the superiority of the new algorithm.

Furniture typically consists of assemblies of elongated and planar parts that are connected together by glue, nails, hinges, screws, or other means that do not encourage disassembly and re-assembly. An alternative approach is to use an interlocking mechanism, where the component parts tightly interlock with one another. The challenge in designing such a network of interlocking joints is that local analysis is insufficient to guarantee global interlocking, and there is a huge number of joint combinations that require an enormous exploration effort to ensure global interlocking. In this paper, we present a computational solution to support the design of a network of interlocking joints that form a globally-interlocking furniture assembly. The key idea is to break the furniture complex into an overlapping set of small groups, where the parts in each group are immobilized by a local key, and adjacent groups are further locked with dependencies. The dependency among the groups saves the effort of exploring the immobilization of every subset of parts in the assembly, thus allowing the intensive interlocking computation to be localized within each small group. We demonstrate the effectiveness of our technique on many globally-interlocking furniture assemblies of various shapes and complexity.

This paper addresses a challenging single-view modeling and animation problem with cartoon images. Our goal is to model the hairs in a given cartoon image with consistent layering and occlusion, so that we can produce various visual effects from just a single image. We propose a novel 2.5D modeling approach to deal with this problem. Given an input image, we first segment the hairs of the cartoon character into regions of hair strands. Then, we apply our novel layering metric, which is derived from the Gestalt psychology, to automatically optimize the depth ordering among the hair strands. After that, we employ our hair completion method to fill the occluded part of each hair strand, and create a 2.5D model of the cartoon hair. By using this model, we can produce various visual effects, e.g., we develop a simplified fluid simulation model to produce wind blowing animations with the 2.5D hairs. To further demonstrate the applicability and versatility of our method, we compare our results with real cartoon hair animations, and also apply our model to produce a wide variety of hair manipulation effects, including hair editing and hair braiding.

Although we can interactively rotate a 3D projected high-dimensional geometry and observe its dynamic changes, this traditional visualization method is limited and highly sensitive to the choice of viewing direction. Parallel-coordinates plots supplement this visualization scenario by providing statistical analysis of the geometry for distinct pairs of co-dimensions. Such analysis results in visual signatures that embed geometric structures such as symmetry, and thus allows us to overview the status of the missing dimensions while exploring the projected geometry. This paper presents a blue-noise sampling approach for efficient construction of continuous parallel-coordinates plots of high-dimensional geometric surfaces defined by mathematical equations. We employ the parallel-coordinates plots with the embedded visual signatures to assist the interactive exploration of high-dimensional geometries, typically for 2-manifold embedded in 4-space. While we interactively explore the 3D projected geometry, we can observe dynamic changes on its visual signature. Various geometric properties can also be identified and visualized. Moreover, we can interactively brush the plots, and see their counterparts in the 3D projection. Assorted geometric properties such as curvature can further be used to enhance the visual signature.

Recognizing handwritten chemical structural formulas is challenging due to the spatial complexity involved, especially for chemical skeletal structural formulas. In chemical skeletal structural formulas, the Carbon atoms are omitted in the drawing of chemical connected bonds, in which the single bonds are connected with hidden Carbon atoms as the connection points. To recognize chemical skeletal structural formulas, it is important to recognize the connected bond strokes and differentiate them from other similar symbols. Moreover, even if the connected bond stroke is identified, it is also challenging to split the connected bond stroke into several single bonds and identify the locations of the hidden Carbon atoms, and its positional relationship in the overall chemical structure. In this paper, we propose a progressive approach for recognizing chemical skeletal structural formulas, in particular the connected bonds. The proposed approach recognizes a chemical formula progressively while the user draws the chemical skeletal structural formula.

This paper presents a novel method that interactively recognizes and vectorizes hand-drawn strokes in front of a commodity webcam. Compared to existing methods, which recognize strokes on a completed drawing, our method captures both spatial and temporal information of the strokes, and faithfully vectorizes them with timestamps. By this, we can avoid various stroke recognition ambiguities, enhance the vectorization quality, and recover the stroke drawing order.

This article explores the application of existing social media platforms for human–robot interaction. With the increasing popularity of social media platforms that connect humans, we propose to portray domestic robots as buddies on the contact list of family members and present a robot management system that employs complementary social media platforms for humans to interact with the vacuuming robot Roomba and a surveillance robot developed on top of iRobot Create. The social media platforms adopted include short message services (SMS), instant messenger (MSN), an online shared calendar (Google Calendar), and a social networking site (Facebook). Hence, we can provide a rich set of user-familiar, intuitive, and highly accessible interfaces, allowing users to flexibly choose their preferred tools in different situations. An in-lab experiment and a multiday field study are conducted to study the characteristics and strengths of each interface and to investigate users’ perception to the robots and behaviors in choosing the interfaces.

This paper presents a novel approach to simulating turbulent flows by developing an adaptive multirelaxation scheme in the framework of lattice Boltzmann equation (LBE). Existing LBE methods in graphics simulations are usually insufficient for turbulent flows since the collision term disturbs the underlying stability and accuracy. We adopt LBE with the multiple relaxation time (MRT) collision model (MRT-LBE), and address this issue by enhancing the collision-term modeling. First, we employ renormalization group analysis and formulate a new turbulence model with an adaptive correction method to compute more appropriate eddy viscosities on a uniform lattice structure. Efficient algebraic calculations are retained with small-scale turbulence details while maintaining the system stability. Second, we note that for MRT-LBE, predicting single eddy viscosity per lattice node may still result in instability. Hence, we simultaneously predict multiple eddy viscosities for stress-tensor-related elements, thereby asynchronously computing multiple relaxation parameters to further enhance the MRT-LBE stability. With these two new strategies, turbulent flows can be simulated with finer visual details even on coarse grid configurations. We demonstrate our results by simulating and visualizing various turbulent flows, particularly with smoke animations, where stable turbulent flows with high Reynolds numbers can be faithfully produced.

Public transportation systems (PTSs) play an important role in modern cities, providing shared/massive transportation services that are essential for the general public. However, due to their increasing complexity, designing effective methods to visualize and explore PTS is highly challenging. Most existing techniques employ network visualization methods and focus on showing the network topology across stops while ignoring various mobility-related factors such as riding time, transfer time, waiting time, and round-the-clock patterns. This work aims to visualize and explore passenger mobility in a PTS with a family of analytical tasks based on inputs from transportation researchers. After exploring different design alternatives, we come up with an integrated solution with three visualization modules: isochrone map view for geographical information, isotime flow map view for effective temporal information comparison and manipulation, and OD-pair journey view for detailed visual analysis of mobility factors along routes between specific origin-destination pairs. The isotime flow map linearizes a flow map into a parallel isoline representation, maximizing the visualization of mobility information along the horizontal time axis while presenting clear and smooth pathways from origin to destinations. Moreover, we devise several interactive visual query methods for users to easily explore the dynamics of PTS mobility over space and time. Lastly, we also construct a PTS mobility model from millions of real passenger trajectories, and evaluate our visualization techniques with assorted case studies with the transportation researchers.

With the growing popularity of pen-based and touch-based devices such as Apple's iPad and Samsung's Galaxy Tablet, handwriting has become an important input method. Although handwriting recognition for text contents and mathematical formulae are well-supported in these devices, recognizing handwritten chemical expressions is still very challenging due to its complex spatial structure. In this research, we focus on chemical symbol recognition which is essential for accurate handwritten chemical expression recognition. In particular, we propose an online hybrid Support Vector Machine - Elastic Matching (SVM-EM) approach for handwritten chemical symbol recognition. Based on the proposed chemical symbol recognition approach and an online structural analysis, we have implemented an online handwritten chemical expression recognition system on Apple's iOS platform. In this paper, we present our proposed SVM-EM approach for handwritten chemical symbol recognition and evaluate it with several users to verify its promising performance as a real application.

Architectural sketching and massing are used by designers to analyze and explore the design space of buildings. This paper describes a novel multi-touch interface for fast architectural sketching and massing of tall buildings. It incorporates a family of multi-touch gestures, enabling one to quickly sketch the 2D contour of a base floor plan and extrude it to model a building with multi-floor structures. Further, it provides a set of gestures to users: select and edit a range of floors; scale contours of a building; copy, paste, and rotate a building, i.e., create a twisted structure; edit profile curves of a building's profile; and collapse and remove a selected range of floors. The multi-touch system also allows users to apply textures or geometric facades to the building, and to compare different designs side-by-side. To guide the design process, we describe interactions with a domain expert, a practicing architect. The final interface is evaluated by architects and students in an architecture Dept., which demonstrates that the system allows rapid conceptual design and massing of novel multi-story building structures.

With the recent emergence of pen-based and touch based input devices such as Apple's iPad and Samsung's Galaxy Tablet, it has become more feasible now to input chemical formulas directly by handwriting, which is more natural and efficient than the traditional template-based input methods. In this paper, we propose an effective graph-based chemical structural analysis approach for online progressive handwritten chemical formula recognition. The proposed approach can progressively generate the recognition result after recognizing each symbol and users can make any corrections to the recognition result immediately. In addition, the proposed approach can recognize both cyclic and non-cyclic chemical structures. Recognizing cyclic structural formulas is challenging as bond orientations are very flexible and the relationships between symbols are much more complex than non-cyclic structural formulas. In this paper, the proposed chemical structural analysis approach and its promising performance results will be presented.

3D telepresence is a next-generation multimedia application, offering remote users an immersive and natural video-conferencing environment with real-time 3D graphics. Kinect sensor, a consumer-grade range camera, facilitates the implementation of some recent 3D telepresence systems. However, conventional data filtering methods are insufficient to handle Kinect depth error because such error is quantized rather than just randomly-distributed. Hence, one could often observe large irregularly-shaped patches of pixels that receive the same depth values from Kinect. To enhance visual quality in 3D telepresence, we propose a novel depth data filtering method for Kinect by means of multi-scale and direction-aware support windows. In addition, we develop a GPU-based CUDA implementation that can perform real-time depth filtering. Results from the experiments show that our method can reconstruct hole-free surfaces that are smoother and less bumpy compared to existing methods like bilateral filtering.

Abstract Massive amount of movement data, such as daily trips made by millions of passengers in a city, are widely available nowadays. They are a highly valuable means not only for unveiling human mobility patterns, but also for assisting transportation planning, in particular for metropolises around the world. In this paper, we focus on a novel aspect of visualizing and analyzing massive movement data, i.e., the interchange pattern, aiming at revealing passenger redistribution in a traffic network. We first formulate a new model of circos figure, namely the interchange circos diagram, to present interchange patterns at a junction node in a bundled fashion, and optimize the color assignments to respect the connections within and between junction nodes. Based on this, we develop a family of visual analysis techniques to help users interactively study interchange patterns in a spatiotemporal manner: 1) multi‐spatial scales: from network junctions such as train stations to people flow across and between larger spatial areas; and 2) temporal changes of patterns from different times of the day. Our techniques have been applied to real movement data consisting of hundred thousands of trips, and we present also two case studies on how transportation experts worked with our interface.

A reciprocal frame (RF) is a self-supported three-dimensional structure made up of three or more sloping rods, which form a closed circuit, namely an RF-unit. Large RF-structures built as complex grillages of one or a few similar RF-units have an intrinsic beauty derived from their inherent self-similar and highly symmetric patterns. Designing RF-structures that span over large domains is an intricate and complex task. In this paper, we present an interactive computational tool for designing RF-structures over a 3D guiding surface, focusing on the aesthetic aspect of the design. There are three key contributions in this work. First, we draw an analogy between RF-structures and plane tiling with regular polygons, and develop a computational scheme to generate coherent RF-tessellations from simple grammar rules. Second, we employ a conformal mapping to lift the 2D tessellation over a 3D guiding surface, allowing a real-time preview and efficient exploration of wide ranges of RF design parameters. Third, we devise an optimization method to guarantee the collinearity of contact joints along each rod, while preserving the geometric properties of the RF-structure. Our tool not only supports the design of wide variety of RF pattern classes and their variations, but also allows preview and refinement through interactive controls.

This paper introduces double-sided 2.5D graphics, aiming at enriching the visual appearance when manipulating conventional 2D graphical objects in 2.5D worlds. By attaching a back texture image on a single-sided 2D graphical object, we can enrich the surface and texture detail on 2D graphical objects and improve our visual experience when manipulating and animating them. A family of novel operations on 2.5D graphics, including rolling, twisting, and folding, are proposed in this work, allowing users to efficiently create compelling 2.5D visual effects. Very little effort is needed from the user's side. In our experiment, various creative designs on double-sided graphics were worked out by the recruited participants including a professional artist, which show and demonstrate the feasibility and applicability of our proposed method.

Commercial 3D scene acquisition systems such as the Microsoft Kinect sensor can reduce the cost barrier of realizing mid-air interaction. However, since it can only sense hand position but not hand orientation robustly, current mid-air interaction methods for 3D virtual object manipulation often require contextual and mode switching to perform translation, rotation, and scaling, thus preventing natural continuous gestural interactions. A novel handle bar metaphor is proposed as an effective visual control metaphor between the user's hand gestures and the corresponding virtual object manipulation operations. It mimics a familiar situation of handling objects that are skewered with a bimanual handle bar. The use of relative 3D motion of the two hands to design the mid-air interaction allows us to provide precise controllability despite the Kinect sensor's low image resolution. A comprehensive repertoire of 3D manipulation operations is proposed to manipulate single objects, perform fast constrained rotation, and pack/align multiple objects along a line. Three user studies were devised to demonstrate the efficacy and intuitiveness of the proposed interaction techniques on different virtual manipulation scenarios.

Due to the convenience of taking pictures with various digital cameras and mobile devices, people often end up with multiple shots of the same scene with only slight variations. To enhance photo triaging, which is a very common photowork activity, we propose an effective and easy-to-use brush-and-drag interface that allows the user to interactively explore and compare photos within a broader scene context. First, we brush to mark an area of interest on a photo with our finger(s); our tailored segmentation engine automatically determines corresponding image elements among the photos. Then, we can drag the segmented elements from different photos across the screen to explore them simultaneously, and further perform simple finger gestures to interactively rank photos, select favorites for sharing, or to remove unwanted ones. This novel interaction method was implemented on a consumer-level tablet computer and demonstrated to offer effective interactions in a user study.

Interlocking puzzles are very challenging geometric problems with the fascinating property that once we solve one by putting together the puzzle pieces, the puzzle pieces interlock with one another, preventing the assembly from falling apart. Though interlocking puzzles have been known for hundreds of years, very little is known about the governing mechanics. Thus, designing new interlocking geometries is basically accomplished with extensive manual effort or expensive exhaustive search with computers. In this paper, we revisit the notion of interlocking in greater depth, and devise a formal method of the interlocking mechanics. From this, we can develop a constructive approach for devising new interlocking geometries that directly guarantees the validity of the interlocking instead of exhaustively testing it. In particular, we focus on an interesting subclass of interlocking puzzles that are recursive in the sense that the assembly of puzzle pieces can remain an interlocking puzzle also after sequential removal of pieces; there is only one specific sequence of assembling, or disassembling, such a puzzle. Our proposed method can allow efficient generation of recursive interlocking geometries of various complexities, and by further realizing it with LEGO bricks, we can enable the hand-built creation of custom puzzle games.

Estimating illumination and deformation fields on textures is essential for both analysis and application purposes. Traditional methods for such estimation usually require complicated and sometimes labor-intensive processing. In this paper, we propose a new perspective for this problem and suggest a novel statistical approach which is much simpler and more efficient. Our experiments show that many textures in daily life are statistically invariant in terms of colors and gradients. Variations of such statistics can be assumed to be influenced by illumination and deformation. This implies that we can inversely estimate the spatially varying illumination and deformation according to the variation of the texture statistics. This enables us to decompose a texture photo into an illumination field, a deformation field, and an implicit texture which are illumination- and deformation-free, within a short period of time, and with minimal user input. By processing and recombining these components, a variety of synthesis effects, such as exemplar preparation, texture replacement, surface relighting, as well as geometry modification, can be well achieved. Finally, convincing results are shown to demonstrate the effectiveness of the proposed method.

Closed geodesics, or geodesic loops, are crucial to the study of differential topology and differential geometry. Although the existence and properties of closed geodesics on smooth surfaces have been widely studied in mathematics community, relatively little progress has been made on how to compute them on polygonal surfaces. Most existing algorithms simply consider the mesh as a graph and so the resultant loops are restricted only on mesh edges, which are far from the actual geodesics. This paper is the first to prove the existence and uniqueness of geodesic loop restricted on a closed face sequence; it contributes also with an efficient algorithm to iteratively evolve an initial closed path on a given mesh into an exact geodesic loop within finite steps. Our proposed algorithm takes only an O(k) space complexity and an O(mk) time complexity (experimentally), where m is the number of vertices in the region bounded by the initial loop and the resultant geodesic loop, and k is the average number of edges in the edge sequences that the evolving loop passes through. In contrast to the existing geodesic curvature flow methods which compute an approximate geodesic loop within a predefined threshold, our method is exact and can apply directly to triangular meshes without needing to solve any differential equation with a numerical solver; it can run at interactive speed, e.g., in the order of milliseconds, for a mesh with around 50K vertices, and hence, significantly outperforms existing algorithms. Actually, our algorithm could run at interactive speed even for larger meshes. Besides the complexity of the input mesh, the geometric shape could also affect the number of evolving steps, i.e., the performance. We motivate our algorithm with an interactive shape segmentation example shown later in the paper.

While very large collaborative surfaces are already being widely employed to facilitate concurrent interactions with multiple users, they involve no personalization in the touch interactions. Augmenting them to identify the touch interactions with multiple smart-phones can enable interesting co-located communal applications with context-based personalized interactions and information exchange amongst users' portable devices and the shared wall display. This paper proposes a novel matching technique, called tilt correlation, which employs the built-in tilt sensor to identify smart-phones that make concurrent two-point contacts on a common multi-touch wall display. Experimental investigations suggest that the resultant error rate is relatively low; in addition, we also propose a quantitative measure, called the Bourne Identity Index to allow application designers to determine the reliability of each device identification.

Visual exploration of volume data often requires the user to manipulate the orientation and position of a slicing plane in order to observe, annotate or measure its internal structures. Such operations, with its many degrees of freedom in 3D space, map poorly into interaction modalities afforded by mouse-keyboard interfaces or flat multi-touch displays alone. We addressed this problem using a what-you-see-is-what-you-feel (WYSIWYF) approach, which integrates the natural user interface of a multi-touch wall display with the untethered physical dexterity provided by a handheld device with multi-touch and 3D-tilt sensing capabilities. A slicing plane can be directly and intuitively manipulated at any desired position within the displayed volume data using a commonly available mobile device such as the iPod touch. 2D image slices can be transferred wirelessly to this small touch screen device, where a novel fast fat finger annotation technique (F3AT) is proposed to perform accurate and speedy contour drawings. Our user studies support the efficacy of our proposed visual exploration and annotation interaction designs.

Diffusion curves are effective 2D vector-graphics primitives, for creating smoothly-shaded drawings with rich colors and unique styles. Conventional drawing systems for diffusion curves often require users to successively layout curve geometry and then specify colors, which is rather tedious for complex drawings. This paper proposes a novel multi-touch sketching interface for efficient design of 2D vector graphics with diffusion curves. In sharp contrast to previous interfaces, we develop a family of multi-touch gestures, allowing users to simultaneously sketch multiple diffusion curves and also to interactively edit and tune curve geometry and colors. Our experiments show that this not only brings novel painting experience to users but also provides a practical and effective tool for vector graphics design, useful for styles like silk painting, Disney cartoon, art poster, and photo-realistic effects. Lastly, we conduct a user study to explore the interface's intuitive and efficient drawing capability with both professional 2D artists and novice users.

A 3D burr puzzle is a 3D model that consists of interlocking pieces with a single-key property. That is, when the puzzle is assembled, all the pieces are notched except one single key component which remains mobile. The intriguing property of the assembled burr puzzle is that it is stable, perfectly interlocked, without glue or screws, etc. Moreover, a burr puzzle consisting of a small number of pieces is still rather difficult to solve since the assembly must follow certain orders while the combinatorial complexity of the puzzle's piece arrangements is extremely high. In this paper, we generalize the 6-piece orthogonal burr puzzle (a knot) to design and model burr puzzles from 3D models. Given a 3D input model, we first interactively embed a network of knots into the 3D shape. Our method automatically optimizes and arranges the orientation of each knot, and modifies pieces of adjacent knots with an appropriate connection type. Then, following the geometry of the embedded pieces, the entire 3D model is partitioned by splitting the solid while respecting the assembly motion of embedded pieces. The main technical challenge is to enforce the single-key property and ensure the assembly/disassembly remains feasible, as the puzzle pieces in a network of knots are highly interlocked. Lastly, we also present an automated approach to generate the visualizations of the puzzle assembly process.

Enabling efficient exploration of large-scale virtual environments such as those simulating astrophysical environments is highly challenging. Astrophysical virtual worlds span exceptionally large spatial scales occupied mostly by empty space, and this makes it difficult for the user to comprehend the spatial context during exploratory navigation. Public exhibits, where novice users have little experience using complicated virtual navigation interfaces, pose additional challenges.

Painting on 3D surfaces is an important operation in computer graphics, virtual reality, and computer aided design. The painting styles in existing WYSIWYG systems can be awkward, due to the difficulty in rotating or aligning an object for proper viewing during the painting. This paper proposes a multi-layer approach to building a practical, robust, and novel WYSIWYG interface for efficient painting on 3D models. The paintable area is not limited to the front-most visible surface on the screen as in conventional WYSIWYG interfaces. We can efficiently and interactively draw long strokes across different depth layers, and unveil occluded regions that one would like to see or paint on. In addition, since the painting is now depth-sensitive, we can avoid various potential painting artifacts and limitations in the conventional painting interfaces. This multi-layer approach brings in several novel painting operations that contribute to a more compelling WYSIWYG 3D painting interface; this is particular useful when dealing with complicated objects with occluded parts and objects that cannot be easily parameterized. We evaluated our system with 23 users, including both artists and novice painters, and obtained positive experimental results and feedback from them. The user study results demonstrate the efficacy of our novel interface over conventional painting interfaces.

Capacity constrained Voronoi tessellation (CCVT) [Balzer et al. 2009] addresses a crucial quality issue of Lloyd relaxation but at the expense of slower computation, which could hinder its potential wide adoption. We present a fast capacity constrained Voronoi tessellation algorithm which is orders of magnitude faster than the original method proposed by Balzer et al. [2009] (and 10x faster than a previous accelerated implementation of the same technique) while maintaining excellent distribution quality and scaling very well as the number of points increase.

This paper introduces a method for optimizing the tiles of a quad-mesh. Given a quad-based surface, the goal is to generate a set of K quads whose instances can produce a tiled surface that approximates the input surface. A solution to the problem is a K-set tilable surface, which can lead to an effective cost reduction in the physical construction of the given surface. Rather than molding lots of different building blocks, a K-set tilable surface requires the construction of K prefabricated components only. To realize the K-set tilable surface, we use a cluster-optimize approach. First, we iteratively cluster and analyze: clusters of similar shapes are merged, while edge connections between the K quads on the target surface are analyzed to learn the induced flexibility of the K-set tilable surface. Then, we apply a non-linear optimization model with constraints that maintain the K quads connections and shapes, and show how quad-based surfaces are optimized into K-set tilable surfaces. Our algorithm is demonstrated on various surfaces, including some that mimic the exteriors of certain renowned building landmarks.

Blue noise sampling is widely employed for a variety of imaging, geometry, and rendering applications. However, existing research so far has focused mainly on isotropic sampling, and challenges remain for the anisotropic scenario both in sample generation and quality verification. We present anisotropic blue noise sampling to address these issues. On the generation side, we extend dart throwing and relaxation, the two classical methods for isotropic blue noise sampling, for the anisotropic setting, while ensuring both high-quality results and efficient computation. On the verification side, although Fourier spectrum analysis has been one of the most powerful and widely adopted tools, so far it has been applied only to uniform isotropic samples. We introduce approaches based on warping and sphere sampling that allow us to extend Fourier spectrum analysis for adaptive and/or anisotropic samples; thus, we can detect problems in alternative anisotropic sampling techniques that were not yet found via prior verification. We present several applications of our technique, including stippling, visualization, surface texturing, and object distribution.

This article introduces an optimization approach for modeling and rendering impossible figures. Our solution is inspired by how modeling artists construct physical 3D models to produce a valid 2D view of an impossible figure. Given a set of 3D locally possible parts of the figure, our algorithm automatically optimizes a view-dependent 3D model, subject to the necessary 3D constraints for rendering the impossible figure at the desired novel viewpoint. A linear and constrained least-squares solution to the optimization problem is derived, thereby allowing an efficient computation and rendering new views of impossible figures at interactive rates. Once the optimized model is available, a variety of compelling rendering effects can be applied to the impossible figure.

This paper presents an interactive visualization tool to study and analyze hyperspectral images (HSI) of historical documents. This work is part of a collaborative effort with the Nationaal Archief of the Netherlands (NAN) and Art Innovation, a manufacturer of hyperspectral imaging hardware designed for old and fragile documents. The NAN is actively capturing HSI of historical documents for use in a variety of tasks related to the analysis and management of archival collections, from ink and paper analysis to monitoring the effects of environmental aging. To assist their work, we have developed a comprehensive visualization tool that offers an assortment of visualization and analysis methods, including interactive spectral selection, spectral similarity analysis, time-varying data analysis and visualization, and selective spectral band fusion. This paper describes our visualization software and how it is used to facilitate the tasks needed by our collaborators. Evaluation feedback from our collaborators on how this tool benefits their work is included.

Omnidirectional videos are usually mapped to planar domain for encoding with off-the-shelf video compression standards. However, existing work typically neglects the effect of the sphere-to-plane mapping. In this paper, we show that by carefully designing the mapping, we can improve the visual quality, stability and compression efficiency of encoding omnidirectional videos. Here we propose a novel mapping scheme, known as the rhombic dodecahedron map (RD map) to represent data over the spherical domain. By using a family of skew great circles as the subdivision kernel, the RD map not only produces a sampling pattern with very low discrepancy, it can also support a highly efficient data indexing mechanism over the spherical domain. Since the proposed map is quad-based, geodesic-aligned, and of very low area and shape distortion, we can reliably apply 2-D wavelet-based and DCT-based encoding methods that are originally designated to planar perspective videos. At the end, we perform a series of analysis and experiments to investigate and verify the effectiveness of the proposed method; with its ultra-fast data indexing capability, we show that we can playback omnidirectional videos with very high frame rates on conventional PCs with GPU support.

This paper presents a computer-aided geometric design approach to realize a new genre of 3D puzzle, namely the 3D Polyomino puzzle . We base our puzzle pieces on the family of 2D shapes known as polyominoes in recreational mathematics, and construct the 3D puzzle model by covering its geometry with polyominolike shapes. We first apply quad-based surface parametrization to the input solid, and tile the parametrized surface with polyominoes. Then, we construct a nonintersecting offset surface inside the input solid and shape the puzzle pieces to fit inside a thick shell volume. Finally, we develop a family of associated techniques for precisely constructing the geometry of individual puzzle pieces, including the ring-based ordering scheme, the motion space analysis technique, and the tab and blank construction method. The final completed puzzle model is guaranteed to be not only buildable, but also interlocking and maintainable.

This paper describes GL4D, an interactive system for visualizing 2-manifolds and 3-manifolds embedded in four Euclidean dimensions and illuminated by 4D light sources. It is a tetrahedron-based rendering pipeline that projects geometry into volume images, an exact parallel to the conventional triangle-based rendering pipeline for 3D graphics. Novel features include GPU-based algorithms for real-time 4D occlusion handling and transparency compositing; we thus enable a previously impossible level of quality and interactivity for exploring lit 4D objects. The 4D tetrahedrons are stored in GPU memory as vertex buffer objects, and the vertex shader is used to perform per-vertex 4D modelview transformations and 4D-to-3D projection. The geometry shader extension is utilized to slice the projected tetrahedrons and rasterize the slices into individual 2D layers of voxel fragments. Finally, the fragment shader performs per-voxel operations such as lighting and alpha blending with previously computed layers. We account for 4D voxel occlusion along the 4D-to-3D projection ray by supporting a multi-pass back-to-front fragment composition along the projection ray; to accomplish this, we exploit a new adaptation of the dual depth peeling technique to produce correct volume image data and to simultaneously render the resulting volume data using 3D transfer functions into the final 2D image. Previous CPU implementations of the rendering of 4D-embedded 3-manifolds could not perform either the 4D depth-buffered projection or manipulation of the volume-rendered image in real-time; in particular, the dual depth peeling algorithm is a novel GPU-based solution to the real-time 4D depth-buffering problem. GL4D is implemented as an integrated OpenGL-style API library, so that the underlying shader operations are as transparent as possible to the user.

With recent advances in the measurement technology for allsky astrophysical imaging, our view of the sky is no longer limited to the tiny visible spectral range over the 2D Celestial sphere. We now can access a third dimension corresponding to a broad electromagnetic spectrum with a wide range of allsky surveys; these surveys span frequency bands including long wavelength radio, microwaves, very short X-rays, and gamma rays. These advances motivate us to study and examine multiwavelength visualization techniques to maximize our capabilities to visualize and exploit these informative image data sets. In this work, we begin with the processing of the data themselves, uniformizing the representations and units of raw data obtained from varied detector sources. Then we apply tools to map, convert, color-code, and format the multiwavelength data in forms useful for applications. We explore different visual representations for displaying the data, including such methods as textured image stacks, the horseshoe representation, and GPU-based volume visualization. A family of visual tools and analysis methods is introduced to explore the data, including interactive data mapping on the graphics processing unit (GPU), the mini-map explorer, and GPU-based interactive feature analysis.

This paper introduces a novel surface-modeling method to stochastically distribute features on arbitrary topological surfaces. The generated distribution of features follows the Poisson disk distribution, so we can have a minimum separation guarantee between features and avoid feature overlap. With the proposed method, we not only can interactively adjust and edit features with the help of the proposed Poisson disk map, but can also efficiently re-distribute features on object surfaces. The underlying mechanism is our dual tiling scheme, known as the Dual Poisson-Disk Tiling. First, we compute the dual of a given surface parameterization, and tile the dual surface by our specially-designed dual tiles; during the pre-processing, the Poisson disk distribution has been pre-generated on these tiles. By dual tiling, we can nicely avoid the problem of corner heterogeneity when tiling arbitrary parameterized surfaces, and can also reduce the tile set complexity. Furthermore, the dual tiling scheme is non-periodic, and we can also maintain a manageable tile set. To demonstrate the applicability of this technique, we explore a number of surface-modeling applications: pattern and shape distribution, bump-mapping, illustrative rendering, mold simulation, the modeling of separable features in texture and BTF, and the distribution of geometric textures in shell space.

This paper proposes to perform reaction-diffusion on surface tiles. The square tiles fit nicely and cost-effectively in GPU memory, whereas we also apply distortion minimization on tiles so as to precisely reduce the unbalanced scale and resolution problem of chemicals in the reaction- diffusion. The interconnection nature of tiles accounts for the surface topology, and thus allows the chemicals to flow naturally over surfaces of arbitrary genus. Furthermore, by taking advantage of the tile structure, we can efficiently perform localized reaction-diffusion, and adjust the pattern formulation in an interactive manner on the GPU. To demonstrate its performance, we develop an interactive system that allows texture designers to fine-tune and alter the reaction-diffusion process by directly painting chemicals onto the object surface. Finally, we also develop several non-trivial applications of reaction-diffusion, including the geometry-dependent reaction-diffusion and deformation-aware reaction-diffusion.

We present a novel method for synthesizing solid textures from 2D texture exemplars. First, we extend 2D texture optimization techniques to synthesize 3D texture solids. Next, the non-parametric texture optimization approach is integrated with histogram matching, which forces the global statistics of the synthesized solid to match those of the exemplar. This improves the convergence of the synthesis process and enables using smaller neighborhoods. In addition to producing compelling texture mapped surfaces, our method also effectively models the material in the interior of solid objects. We also demonstrate that our method is well-suited for synthesizing textures with a large number of channels per texel.

Modern astronomical instruments produce enormous amounts of three-dimensional data describing the physical Universe. The currently available data sets range from the solar system to nearby stars and portions of the Milky Way Galaxy, including the interstellar medium and some extrasolar planets, and extend out to include galaxies billions of light years away. Because of its gigantic scale and the fact that it is dominated by empty space, modeling and rendering the Universe is very different from modeling and rendering ordinary three-dimensional virtual worlds at human scales. Our purpose is to introduce a comprehensive approach to an architecture solving this visualization problem that encompasses the entire Universe while seeking to be as scale-neutral as possible. One key element is the representation of model-rendering procedures using power scaled coordinates (PSC), along with various PSC-based techniques that we have devised to generalize and optimize the conventional graphics framework to the scale domains of astronomical visualization. Employing this architecture, we have developed an assortment of scale-independent modeling and rendering methods for a large variety of astronomical models, and have demonstrated scale-insensitive interactive visualizations of the physical Universe covering scales ranging from human scale to the Earth, to the solar system, to the Milky Way Galaxy, and to the entire observable Universe.

This paper presents a modular framework to efficiently apply the bidirectional texture functions (BTF) onto object surfaces. The basic building blocks are the BTF tiles. By constructing one set of BTF tiles, a wide variety of objects can be textured seamlessly without re-synthesizing the BTF. The proposed framework nicely decouples the surface appearance from the geometry. With this appearance-geometry decoupling, one can build a library of BTF tile sets to instantaneously dress and render various objects under variable lighting and viewing conditions. The core of our framework is a novel method for synthesizing seamless high-dimensional BTF tiles, that are difficult for existing synthesis techniques. Its key is to shorten the cutting paths and broaden the choices of samples so as to increase the chance of synthesizing seamless BTF tiles. To tackle the enormous data, the tile synthesis process is performed in compressed domain. This not just allows the handling of large BTF data during the synthesis, but also facilitates compact storage of the BTF in GPU memory during the rendering.

Visualization of uncertainty or error in astrophysical data is seldom available in simulations of astronomical phenomena, and yet almost all rendered attributes possess some degree of uncertainty due to observational error. Uncertainties associated with spatial location typically vary signicantly with scale and thus introduce further complexity in the interpretation of a given visualization. This paper introduces effective techniques for visualizing uncertainty in large-scale virtual astrophysical environments. Building upon our previous transparently scalable visualization architecture, we develop tools that enhance the perception and comprehension of uncertainty across wide scale ranges. Our methods include a unified color-coding scheme for representing log-scale distances and percentage errors, an ellipsoid model to represent positional uncertainty, an ellipsoid envelope model to expose trajectory uncertainty, and a magic-glass design supporting the selection of ranges of log-scale distance and uncertainty parameters, as well as an overview mode and a scalable WIM tool for exposing the magnitudes of spatial context and uncertainty.

Navigating through large-scale virtual environments such as simulations of the astrophysical Universe is difficult. The huge spatial range of astronomical models and the dominance of empty space make it hard for users to travel across cosmological scales effectively, and the problem of wayfinding further impedes the user's ability to acquire reliable spatial knowledge of astronomical contexts. We introduce a new technique called the scalable world-in-miniature (WIM) map as a unifying interface to facilitate travel and wayfinding in a virtual environment spanning gigantic spatial scales: Power-law spatial scaling enables rapid and accurate transitions among widely separated regions; logarithmically mapped miniature spaces offer a global overview mode when the full context is too large; 3D landmarks represented in the WIM are enhanced by scale, positional, and directional cues to augment spatial context awareness; a series of navigation models are incorporated into the scalable WIM to improve the performance of travel tasks posed by the unique characteristics of virtual cosmic exploration. The scalable WIM user interface supports an improved physical navigation experience and assists pragmatic cognitive understanding of a visualization context that incorporates the features of large-scale astronomy.

We propose a novel 2D representation for 3D visibility sorting, the Binary-Space-Partitioned Image (BSPI), to accelerate real-time image-based rendering. BSPI is an efficient 2D realization of a 3D BSP tree, which is commonly used in computer graphics for time-critical visibility sorting. Since the overall structure of a BSP tree is encoded in a BSPI, traversing a BSPI is comparable to traversing the corresponding BSP tree. BSPI performs visibility sorting efficiently and accurately in the 2D image space by warping the reference image triangle-by-triangle instead of pixel-by-pixel. Multiple BSPIs can be combined to solve "disocclusion," when an occluded portion of the scene becomes visible at a novel viewpoint. Our method is highly automatic, including a tensor voting preprocessing step that generates candidate image partition lines for BSPIs, filters the noisy input data by rejecting outliers, and interpolates missing information. Our system has been applied to a variety of real data, including stereo, motion, and range images.

Image-based modeling and rendering has been demonstrated as a cost-effective and efficient approach to virtual reality applications. The computational model that most image-based techniques are based on is the plenoptic function. Since the original formulation of the plenoptic function does not include illumination, most previous image-based virtual reality applications simply assume that the illumination is fixed. We propose a formulation of the plenoptic function, called the plenoptic illumination function, which explicitly specifies the illumination component. Techniques based on this new formulation can be extended to support relighting as well as view interpolation. To relight images with various illumination configurations, we also propose a local illumination model, which utilizes the rules of image superposition. We demonstrate how this new formulation can be applied to extend two existing image-based representations, panorama representation such as QuickTime VR and two-plane parameterization, to support relighting with trivial modifications. The core of this framework is compression, and we therefore show how to exploit two types of data correlation, the intra-pixel and the inter-pixel correlations, in order to achieve a manageable storage size.

The automatic conversion of floating point software implementations of algorithms to a equivalent fixed point implementation which can be efficiently implemented in an FCCM remains an obstacle in the rapid systems prototyping design flow. Floating point to fixed point conversion is tedious, error prone and requires a good knowledge of fixed point computer arithmetic. This paper describes a software system called fp designed to automate the process. It consists of a fixed point C++ class; a profiler which is used to determine the number of bits of precision required for each signal in the hardware implementation; an optimiser which finds the minimal number of bits required for a specified degree of accuracy in the implementation and finally and a compiler which takes the information collected by the system and outputs synthesisable VHDL code. A post-rendering 3D image warping application designed using this system is used as an example.

Recent advances in image-based rendering techniques allow us to have interactive panoramic viewing of real world environment using real photos. With panorama visualization tools like QuickTime VR or Realspace Viewer, we are able to have fast navigation in an image-based environment. However, the navigation control is restricted to panning, zooming and tilting of a single panoramic view. Smooth walkthrough between panoramic nodes is not yet supported. In this paper, we first describe how we apply the epipolar geometry between cylindrical projection manifolds to find point correspondences between real-world panoramic photos. A correspondence matching program is developed to allow users to identify correspondence interactively. The correspondence information is identified by defining patches on the panoramic image. Then, the system can generate a triangular mesh for the panorama based on the given patches. After that, we are able to provide free navigation between panoramic nodes by means of the triangle-based image warping technique.