Despite significant progress in text-driven 4D human-object interaction (HOI) generation with supervised methods, the scalability remains limited by the scarcity of large-scale 4D HOI datasets. To overcome this, recent approaches attempt zero-shot 4D HOI generation with pre-trained image diffusion models. However, interaction cues are minimally distilled during the generation process, restricting their applicability across diverse scenarios. In this paper, we propose AnchorHOI, a novel framework that thoroughly exploits hybrid priors by incorporating video diffusion models beyond image diffusion models, advancing 4D HOI generation. Nevertheless, directly optimizing high-dimensional 4D HOI with such priors remains challenging, particularly for human pose and compositional motion. To address this challenge, AnchorHOI introduces an anchor-based prior distillation strategy, which constructs interaction-aware anchors and then leverages them to guide generation in a tractable two-step process. Specifically, two tailored anchors are designed for 4D HOI generation: anchor Neural Radiance Fields (NeRFs) for expressive interaction composition, and anchor keypoints for realistic motion synthesis. Extensive experiments demonstrate that AnchorHOI outperforms previous methods with superior diversity and generalization.

Abstract In recent years, 3D editing has become a significant research topic, primarily due to its ability to manipulate 3D assets in ways that fulfill the growing demand for personalized customization. The advent of radiance field-based methods, exemplified by pioneering frameworks such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), represents a pivotal innovation in scene representation and novel view synthesis, greatly enhancing the effectiveness and efficiency of 3D editing. This survey provides a comprehensive overview of the current advancements in 3D editing based on NeRF and 3DGS, systematically categorizing existing methods according to specific editing tasks while analyzing the current challenges and potential research directions. Our goal through this survey is to offer a comprehensive and valuable resource for researchers in the field, encouraging innovative ideas that may drive further progress in 3D editing.

Learning neural implicit fields of 3D shapes is a rapidly emerging field that enables shape representation at arbitrary resolutions. Due to the flexibility, neural implicit fields have succeeded in many research areas, including shape reconstruction, novel view image synthesis, and more recently, object pose estimation. Neural implicit fields enable learning dense correspondences between the camera space and the object's canonical space - including unobserved regions in camera space - significantly boosting object pose estimation performance in challenging scenarios like highly occluded objects and novel shapes. Despite progress, predicting canonical coordinates for unobserved camera-space regions remains challenging due to the lack of direct observational signals. This necessitates heavy reliance on the model's generalization ability, resulting in high uncertainty. Consequently, densely sampling points across the entire camera space may yield inaccurate estimations that hinder the learning process and compromise performance. To alleviate this problem, we propose a method combining an SO(3)-equivariant convolutional implicit network and a positive-incentive point sampling (PIPS) strategy. The SO(3)-equivariant convolutional implicit network estimates point-level attributes with SO(3)-equivariance at arbitrary query locations, demonstrating superior performance compared to most existing baselines. The PIPS strategy dynamically determines sampling locations based on the input, thereby boosting the network's accuracy and training efficiency. The PIPS strategy is implemented with a PIPS estimation network which generates sparse sample points with distinctive features capable of determining all object pose DoFs with high certainty. To collect the training data of the PIPS estimation network, we propose to automatically generate the pseudo ground-truth with a teacher model. Our method outperforms the state-of-the-art on three pose estimation datasets. It achieves 0.63 in the $5^{\circ }2$5∘2 cm metric on NOCS-REAL275, 0.62 in the $5^{\circ }5$5∘5 cm metric on ShapeNet-C, and 77.3 in the AR metric on LineMOD-O. Notably, it demonstrates significant improvements in challenging scenarios, such as objects captured with unseen pose, high occlusion, novel geometry, and severe noise.

The challenging task of 3D planar reconstruction from images involves several sub-tasks including frame-wise plane detection, segmentation, parameter regression and possibly depth prediction, along with cross-frame plane correspondence and relative camera pose estimation. Previous works adopt a divide and conquer strategy, addressing above sub-tasks with distinct network modules in a two-stage paradigm. Specifically, given an initial camera pose and per-frame plane predictions from the first stage, further exclusively designed modules relying on external plane correspondence labeling are applied to merge multi-view plane entities and produce refined camera pose. Notably, existing work fails to integrate these closely related sub-tasks into a unified framework, and instead addresses them separately and sequentially, which we identify as a primary source of performance limitations. Motivated by this finding and the success of query-based learning in enriching reasoning among semantic entities, in this paper, we propose PlaneRecTR++, a Transformer-based architecture, which for the first time unifies all tasks of multi-view planar reconstruction and pose estimation within a compact single-stage framework, eliminating the need for the initial pose estimation and supervision of plane correspondence. Extensive quantitative and qualitative experiments demonstrate that our proposed unified learning achieves mutual benefits across sub-tasks, achieving a new state-of-the-art performance on the public ScanNetv1, ScanNetv2, NYUv2-Plane, and MatterPort3D datasets.

The introduction of the neural implicit representation has notably propelled the advancement of online dense reconstruction techniques. Compared to traditional explicit representations, such as TSDF, it substantially improves the mapping completeness and memory efficiency. However, the lack of reconstruction details and the time-consuming learning of neural representations hinder the widespread application of neural-based methods to large-scale online reconstruction. We introduce RemixFusion, a novel residual-based mixed representation for scene reconstruction and camera pose estimation dedicated to high-quality and large-scale online RGB-D reconstruction. In particular, we propose a residual-based map representation comprised of an explicit coarse TSDF grid and an implicit neural module that produces residuals representing fine-grained details to be added to the coarse grid. Such mixed representation allows for detail-rich reconstruction with bounded time and memory budget, contrasting with the overly-smoothed results by the purely implicit representations, thus paving the way for high-quality camera tracking. Furthermore, we extend the residual-based representation to handle multi-frame joint pose optimization via bundle adjustment (BA). In contrast to the existing methods, which optimize poses directly, we opt to optimize pose changes. Combined with a novel technique for adaptive gradient amplification, our method attains better optimization convergence and global optimality. Furthermore, we adopt a local moving volume to factorize the whole mixed scene representation with a divide-and-conquer design to facilitate efficient online learning in our residual-based framework. Extensive experiments demonstrate that our method surpasses all state-of-the-art ones, including those based either on explicit or implicit representations, in terms of the accuracy of both mapping and tracking on large-scale scenes. Project page can be found at https://lanlan96.github.io/RemixFusion/ .

The household rearrangement task involves spotting misplaced objects in a scene and accommodate them with proper places. It depends both on common-sense knowledge on the objective side and human user preference on the subjective side. In achieving such a task, we propose to mine object functionality with user preference alignment directly from the scene itself, without relying on human intervention. To do so, we work with scene graph representation and propose LLM-enhanced scene graph learning which transforms the input scene graph into an Affordance Enhanced Graph (AEG) with information-enriched nodes and newly discovered edges (relations). In AEG, the nodes corresponding to the receptacle objects are augmented with context-induced affordance which encodes what kind of carriable objects can be placed on it. New edges are discovered with newly discovered non-local relations. With AEG, we perform task planning for scene rearrangement by detecting misplaced carriables and determining a proper placement for each of them. We implement an end-to-end robot system for autonomous household rearrangement in unseen environments and test our method by implementing a tiding robot in both simulated environments and real-world scenarios, and perform evaluation on a new benchmark we build. Extensive evaluations demonstrate that our method achieves state-of-the-art performance in misplacement detection and rearrangement planning.

Estimating the 6-DoF posture of parts in assembly-based modeling is a critical task in the fields of computer graphics, computer vision and robotics. A typical scenario involves enabling a machine agent to automatically assemble IKEA furniture using the provided parts. This paper presents HiFormer, a novel Hierarchical Transformer with Box-packed Positional Encoding, designed for highly automatic 3D part assembly. Our method addresses three important issues commonly encountered in 3D part assembly: 1) How to mitigate the overfitting problem associated with Transformer-based feature learning for 3D point clouds? 2) How to effectively model the relationships between the intragroup and intergroup parts? 3) How to compute positional encoding and integrate it into the Transformer for parts with diverse geometric forms in the coarse-to-fine assembly process? These challenges are tackled through three key contributions: 1) a multi-task 3D Swin Transformer with a two-stage training strategy for feature extraction, 2) a novel hierarchical Transformer for capturing part relationships at flattening, intragroup, and intergroup levels, and 3) an innovative box-packed positional encoding that enhances the Transformer by incorporating query, key, and value information derived from relative box positions. On the PartNet benchmark, our method outperforms the state-of-the-art PWH-MP model on three representative categories-Chair, Table, and Lamp-, achieving average improvements of 2.84% in Part Accuracy (PA) and 3.72% in Connection Accuracy (CA) for diversity modeling (with noise), and 3.55% in PA and 3.21% in CA for deterministic modeling (without noise).

We tackle the challenge of concurrent reconstruction at the part level with the RGB appearance and estimation of motion parameters for building digital twins of articulated objects using the 3D Gaussian Splatting (3D-GS) method. With two distinct sets of multi-view imagery, each depicting an object in separate static articulation configurations, we reconstruct the articulated object in 3D Gaussian representations with both appearance and geometry information at the same time. Our approach decoupled multiple highly interdependent parameters through a multi-step optimization process, thereby achieving a stable optimization procedure and high-quality outcomes. We introduce ArticulatedGS, a self-supervised, comprehensive framework that autonomously learns to model shapes and appearances at the part level and synchronizes the optimization of motion parameters, all without reliance on 3D supervision, motion cues, or semantic labels. Our experimental results demonstrate that, among comparable methodologies, our approach has achieved optimal outcomes in terms of part segmentation accuracy, motion estimation accuracy, and visual quality. The code will be made publicly available at our website https://guojunfu-tech.github.io/articulatedGS-io/

Online zero-shot 3D instance segmentation of a progressively reconstructed scene is both a critical and challenging task for embodied applications. With the success of visual foundation models (VFMs) in the image domain, leveraging 2D priors to address 3D online segmentation has become a prominent research focus. Since segmentation results provided by 2D priors often require spatial consistency to be lifted into final 3D segmentation, an efficient method for identifying spatial overlap among 2D masks is essential—yet existing methods rarely achieve this in real time, mainly limiting its use to offline approaches. To address this, we propose an efficient method that lifts 2D masks generated by VFMs into a unified 3D instance using a hashing technique. By employing voxel hashing for efficient 3D scene querying, our approach reduces the time complexity of costly spatial overlap queries from O(n2) to O(n). Accurate spatial associations further enable 3D merging of 2D masks through simple similarity-based filtering in a zero-shot manner, making our approach more robust to incomplete and noisy data. Evaluated on the ScanNet200 and SceneNN benchmarks, our approach achieves state-of-the-art performance in online, zero-shot 3D instance segmentation with leading efficiency. The project page is at https://yjtang249.github.io/OnlineAnySeg.

Despite the typical inversion-then-editing paradigm using text-to-image (T2I) models has demonstrated promising results, directly extending it to text-to-video (T2V) models still suffers severe artifacts such as color flickering and content distortion. Consequently, current video editing methods primarily rely on T2I models, which inherently lack temporal-coherence generative ability, often resulting in inferior editing results. In this paper, we attribute the failure of the typical editing paradigm to: 1) Tightly Spatial-temporal Coupling. The vanilla pivotal-based inversion strategy struggles to disentangle spatial-temporal information in the video diffusion model; 2) Complicated Spatial-temporal Layout. The vanilla cross-attention control is deficient in preserving the unedited content. To address these limitations, we propose a spatial-temporal decoupled guidance (STDG) and multi-frame null-text optimization strategy to provide pivotal temporal cues for more precise pivotal inversion. Furthermore, we introduce a self-attention control strategy to maintain higher fidelity for precise partial content editing. Experimental results demonstrate that our method (termed VideoDirector) effectively harnesses the powerful temporal generation capabilities of T2V models, producing edited videos with state-of-the-art performance in accuracy, motion smoothness, realism, and fidelity to unedited content.

Angiography imaging is a medical imaging technique that enhances the visibility of blood vessels within the body by using contrast agents. Angiographic images can effectively assist in the diagnosis of vascular diseases. However, contrast agents may bring extra radiation exposure which is harmful to patients with health risks. To mitigate these concerns, in this paper, we aim to automatically generate angiography from non-angiographic inputs, by leveraging and enhancing the inherent physical properties of vascular structures. Previous methods relying on 2D slice-based angiography synthesis struggle with maintaining continuity in 3D vascular structures and exhibit limited effectiveness across different imaging modalities. We propose VasTSD, a 3D vascular tree-state space diffusion model to synthesize angiography from 3D non-angiographic volumes, with a novel state space serialization approach that dynamically constructs vascular tree topologies, integrating these with a diffusion-based generative model to ensure the generation of anatomically continuous vasculature in 3D volumes. A pre-trained vision embedder is employed to construct vascular state space representations, enabling consistent modeling of vascular structures across multiple modalities. Extensive experiments on various angiographic datasets demonstrate the superiority of VasTSD over prior works, achieving enhanced continuity of blood vessels in synthesized angiographic synthesis for multiple modalities and anatomical regions. Project page: https://jefferyzhifeng.github.io/projects/VasTSD/

Obtaining enough high-quality correspondences is crucial for robust registration. Existing correspondence refinement methods mostly follow the paradigm of outlier removal, which either fails to correctly identify the accurate correspondences under extreme outlier ratios, or select too few correct correspondences to support robust registration. To address this challenge, we propose a novel approach named Regor, which is a progressive correspondence regenerator that generates higher-quality matches whist sufficiently robust for numerous outliers. In each iteration, we first apply prior-guided local grouping and generalized mutual matching to generate the local region correspondences. A powerful center-aware three-point consistency is then presented to achieve local correspondence correction, instead of removal. Further, we employ global correspondence refinement to obtain accurate correspondences from a global perspective. Through progressive iterations, this process yields a large number of high-quality correspondences. Extensive experiments on both indoor and outdoor datasets demonstrate that the proposed Regor significantly outperforms existing outlier removal techniques. More critically, our approach obtain 10 times more correct correspondences than outlier removal methods. As a result, our method is able to achieve robust registration even with weak features. The code is available at [Regor].

Object goal navigation (ObjectNav) is a fundamental task in embodied AI, requiring an agent to locate a target object in previously unseen environments. This task is particularly challenging because it requires both perceptual and cognitive processes, including object recognition and decision-making. While substantial advancements in perception have been driven by the rapid development of visual foundation models, progress on the cognitive aspect remains constrained, primarily limited to either implicit learning through simulator rollouts or explicit reliance on predefined heuristic rules. Inspired by neuroscientific findings demonstrating that humans maintain and dynamically update fine-grained cognitive states during object search tasks in novel environments, we propose CogNav, a framework designed to mimic this cognitive process using large language models. Specifically, we model the cognitive process using a finite state machine comprising fine-grained cognitive states, ranging from exploration to identification. Transitions between states are determined by a large language model based on a dynamically constructed heterogeneous cognitive map, which contains spatial and semantic information about the scene being explored. Extensive evaluations on the HM3D, MP3D, and RoboTHOR benchmarks demonstrate that our cognitive process modeling significantly improves the success rate of ObjectNav at least by relative 14% over the state-of-the-arts.

This paper presents an end-to-end framework for reconstructing 3D parametric curves directly from multi-view edge maps. Contrasting with existing two-stage methods that follow a sequential ``edge point cloud reconstruction and parametric curve fitting'' pipeline, our one-stage approach optimizes 3D parametric curves directly from 2D edge maps, eliminating error accumulation caused by the inherent optimization gap between disconnected stages. However, parametric curves inherently lack suitability for rendering-based multi-view optimization, necessitating a complementary representation that preserves their geometric properties while enabling differentiable rendering. We propose a novel bi-directional coupling mechanism between parametric curves and edge-oriented Gaussian components. This tight correspondence formulates a curve-aware Gaussian representation, \textbf{CurveGaussian}, that enables differentiable rendering of 3D curves, allowing direct optimization guided by multi-view evidence. Furthermore, we introduce a dynamically adaptive topology optimization framework during training to refine curve structures through linearization, merging, splitting, and pruning operations. Comprehensive evaluations on the ABC dataset and real-world benchmarks demonstrate our one-stage method's superiority over two-stage alternatives, particularly in producing cleaner and more robust reconstructions. Additionally, by directly optimizing parametric curves, our method significantly reduces the parameter count during training, achieving both higher efficiency and superior performance compared to existing approaches.

Abstract Open‐vocabulary 3D object detection has gained significant interest due to its critical applications in autonomous driving and embodied AI. Existing detection methods, whether offline or online, typically rely on dense point cloud reconstruction, which imposes substantial computational overhead and memory constraints, hindering real‐time deployment in downstream tasks. To address this, we propose a novel reconstruction‐free online framework tailored for memory‐efficient and real‐time 3D detection. Specifically, given streaming posed RGB‐D video input, we leverage Cubify Anything as a pre‐trained visual foundation model (VFM) for single‐view 3D object detection, coupled with CLIP to capture open‐vocabulary semantics of detected objects. To fuse all detected bounding boxes across different views into a unified one, we employ an association module for correspondences of multi‐views and an optimization module to fuse the 3D bounding boxes of the same instance. The association module utilizes 3D Non‐Maximum Suppression (NMS) and a box correspondence matching module. The optimization module uses an IoU‐guided efficient random optimization technique based on particle filtering to enforce multi‐view consistency of the 3D bounding boxes while minimizing computational complexity. Extensive experiments on CA‐1M and ScanNetV2 datasets demonstrate that our method achieves state‐of‐the‐art performance among online methods. Benefiting from this novel reconstruction‐free paradigm for 3D object detection, our method exhibits great generalization abilities in various scenarios, enabling real‐time perception even in environments exceeding 1000 square meters.

Combinatorial Optimization (CO) problems are fundamentally important in numerous real-world applications across diverse industries, notably computer graphics, characterized by entailing enormous solution space and demanding time-sensitive response. Despite recent advancements in neural solvers, their limited expressiveness struggles to capture the multi-modal nature of CO landscapes. While some research has adopted diffusion models, these methods sample solutions indiscriminately from the entire NP-complete solution space with time-consuming denoising processes, limiting scalability for large-scale problems. We propose DISCO , an efficient DI ffusion S olver for large-scale C ombinatorial O ptimization problems that excels in both solution quality and inference speed. DISCO’s efficacy is twofold: First, it enhances solution quality by constraining the sampling space to a more meaningful domain guided by solution residues, while preserving the multi-modal properties of the output distributions. Second, it accelerates the denoising process through an analytically solvable approach, enabling solution sampling with very few reverse-time steps and significantly reducing inference time. This inference-speed advantage is further amplified by Jittor, a high-performance learning framework based on just-in-time compiling and meta-operators. DISCO delivers strong performance on large-scale Traveling Salesman Problems and challenging Maximal Independent Set benchmarks, with inference duration up to 5.38 times faster than existing diffusion solver alternatives. We apply DISCO to design 2D/3D TSP Art, enabling the generation of fluid stroke sequences at reduced path costs. By incorporating DISCO’s multi-modal property into a divide-and-conquer strategy, it can further generalize to solve unseen-scale instances out of the box.

Object pose estimation and shape reconstruction are inherently coupled tasks although they have so far been studied separately in most existing approaches. A few recent works addressed the problem of joint pose estimation and shape reconstruction, but they found difficulties in handling partial observations and shape ambiguities. An open challenge in this area is to design a mechanism that has the two tasks benefit each other and boost the performance and robustness of both. In this work, we advocate the use of diffusion models for joint estimation of category-level object poses and reconstruction of object geometry. Diffusion models formulate shape reconstruction as a generation process conditioned on input observations. It has two main advantages. First, the iterative inference of diffusion models provides a mechanism for iterative optimization for both pose estimation and shape reconstruction. Second, diffusion models allow multiple outputs starting from different input noises, which would address the problem of ambiguity caused by partial observations. To achieve this, we propose equivariant diffusion model for joint pose estimation and shape reconstruction. The approach consists of an equivariant feature extractor to aggregate features of the input point cloud and a ShapePose diffusion model to generate object pose and shape simultaneously. To avoid training the model on all possible shape poses in the SO(3) space, we propose to augment the diffusion model with A5-group neurons where the neurons are converted into 5D vectors and can be rotated with the alternating group A5. Based on the A5-group neurons, we implement SO(3)-equivariant 3D point convolution and SO(3)-equivariant concatenation, making the entire network SO(3)-equivariant. Moreover, to select the most plausible combination of pose and shape from the generated ones, we propose a geometry-based measure of plausibility for an estimated pose along with a reconstructed shape. Extensive experiments demonstrate the effectiveness of the proposed method. Specifically, our method achieves the state-of-the-art on two public datasets and a new dataset with stacked objects, in terms of shape reconstruction and pose estimation. In particular, we show the proposed method could provide multiple plausible outputs under partial observations and shape ambiguities.

Radiance fields, including NeRFs and 3D Gaussians, demonstrate great potential in high-fidelity rendering and scene reconstruction, while they require a substantial number of posed images as input. COLMAP is frequently employed for preprocessing to estimate poses. However, COLMAP necessitates a large number of feature matches to operate effectively, and struggles with scenes characterized by sparse features, large baselines, or few-view images. We aim to tackle few-view NeRF reconstruction using only 3 to 6 unposed scene images, freeing from COLMAP initializations. Inspired by the idea of calibration boards in traditional pose calibration, we propose a novel approach of utilizing everyday objects, commonly found in both images and real life, as “pose probes”. By initializing the probe object as a cube shape, we apply a dual-branch volume rendering optimization (object NeRF and scene NeRF) to constrain the pose optimization and jointly refine the geometry. PnP matching is used to initialize poses between images incrementally, where only a few feature matches are enough. PoseProbe achieves state-of-the-art performance in pose estimation and novel view synthesis across multiple datasets in experiments. We demonstrate its effectiveness, particularly in few-view and large-baseline scenes where COLMAP struggles. In ablations, using different objects in a scene yields comparable performance, showing that PoseProbe is robust to the choice of probe objects. Our project page is available at:https://zhirui-gao.github.io/PoseProbe.github.io/

Inserting objects into scenes and performing realistic relighting are common applications in augmented reality (AR). Previous methods focused on inserting virtual objects using CAD models or real objects from single-view images, resulting in highly limited AR application scenarios. We introduce a novel pipeline based on Neural Radiance Fields (NeRFs) for seamlessly integrating objects into scenes, from two sets of images depicting the object and scene. This approach enables novel view synthesis, realistic relighting, and supports physical interactions such as shadow casting between objects. The lighting environment is in a hybrid representation of Spherical Harmonics and Spherical Gaussians, representing both high- and low-frequency lighting components very well, and supporting non-Lambertian surfaces. Specifically, we leverage the benefits of volume rendering and introduce an innovative approach for efficient shadow rendering by comparing the depth maps between the camera view and the light source view and generating vivid soft shadows. The proposed method achieves realistic relighting effects in extensive experimental evaluations.

Surface reconstruction from raw point clouds has been studied for decades in the computer graphics community, which is highly demanded by modeling and rendering applications nowadays. Classic solutions, such as Poisson surface reconstruction, require point normals as extra input to perform reasonable results. Modern transformer-based methods can work without normals, while the results are less fine-grained due to limited encoding performance in local fusion from discrete points. We introduce a novel normalized matrix attention transformer (Tensorformer) to perform high-quality reconstruction. The proposedmatrix attentionallows for simultaneous point-wise and channel-wise message passing, while the previous vector attention loses neighbor point information across different channels. It brings more degree of freedom in feature learning and thus facilitates better modeling of local geometries. Our method achieves state-of-the-art on two commonly used datasets, ShapeNetCore and ABC, and attains 4% improvements on IOU on ShapeNet. Our implementation will be released upon acceptance.

We introduce a novel design of parallel-jaw grippers drawing inspiration from pin-pression toys. The proposed pin-pression gripper features a distinctive mechanism in which each finger integrates a 2D array of pins capable of independent extension and retraction. This unique design allows the gripper to instantaneously customize its finger's shape to conform to the object being grasped by dynamically adjusting the extension/retraction of the pins. In addition, the gripper excels in in-hand re-orientation of objects for enhanced grasping stability again via dynamically adjusting the pins. To learn the dynamic grasping skills of pin-pression grippers, we devise a dedicated reinforcement learning algorithm with careful designs of state representation and reward shaping. To achieve a more efficient grasp-while-lift grasping mode, we propose a curriculum learning scheme. Extensive evaluations demonstrate that our design, together with the learned skills, leads to highly flexible and robust grasping with much stronger generality to unseen objects than alternatives. We also highlight encouraging physical results of sim-to-real transfer on a physically manufactured pin-pression gripper, demonstrating the practical significance of our novel gripper design and grasping skill. Demonstration videos for this paper are available at https://github.com/siggraph-pin-pression-gripper/pin-pression-gripper-video.

This article introduces a novel latent 3D diffusion model for generating neural voxel fields with precise part-aware structures and high-quality textures. In comparison to existing methods, this approach incorporates two key designs to guarantee high-quality and accurate part-aware generation. On one hand, we introduce a latent 3D diffusion process for neural voxel fields, incorporating part-aware information into the diffusion process and allowing generation at significantly higher resolutions to capture rich textural and geometric details accurately. On the other hand, a part-aware shape decoder is introduced to integrate the part codes into the neural voxel fields, guiding accurate part decomposition and producing high-quality rendering results. Importantly, part-aware learning establishes structural relationships to generate texture information for similar regions, thereby facilitating high-quality rendering results. We evaluate our approach across eight different data classes through extensive experimentation and comparisons with state-of-the-art methods. The results demonstrate that our proposed method has superior generative capabilities in part-aware shape generation, outperforming existing state-of-the-art methods. Moreover, we have conducted image- and text-guided shape generation via the conditioned diffusion process, showcasing the advanced potential in multi-modal guided shape generation.

Limited by the encoder-decoder architecture, learning-based edge detectors usually have difficulty predicting edge maps that satisfy both correctness and crispness. With the recent success of the diffusion probabilistic model (DPM), we found it is especially suitable for accurate and crisp edge detection since the denoising process is directly applied to the original image size. Therefore, we propose the first diffusion model for the task of general edge detection, which we call DiffusionEdge. To avoid expensive computational resources while retaining the final performance, we apply DPM in the latent space and enable the classic cross-entropy loss which is uncertainty-aware in pixel level to directly optimize the parameters in latent space in a distillation manner. We also adopt a decoupled architecture to speed up the denoising process and propose a corresponding adaptive Fourier filter to adjust the latent features of specific frequencies. With all the technical designs, DiffusionEdge can be stably trained with limited resources, predicting crisp and accurate edge maps with much fewer augmentation strategies. Extensive experiments on four edge detection benchmarks demonstrate the superiority of DiffusionEdge both in correctness and crispness. On the NYUDv2 dataset, compared to the second best, we increase the ODS, OIS (without post-processing) and AC by 30.2%, 28.1% and 65.1%, respectively. Code: https://github.com/GuHuangAI/DiffusionEdge.

Multi-instance point cloud registration estimates the poses of multiple instances of a model point cloud in a scene point cloud. Extracting accurate point correspondences is to the center of the problem. Existing approaches usually treat the scene point cloud as a whole, overlooking the separation of instances. Therefore, point features could be easily polluted by other points from the back-ground or different instances, leading to inaccurate correspondences oblivious to separate instances, especially in cluttered scenes. In this work, we propose MIRETR, Multi-Instance REgistration TRansformer, a coarse-to-fine approach to the extraction of instance-aware correspondences. At the coarse level, it jointly learns instance-aware superpoint features and predicts per-instance masks. With instance masks, the influence from outside of the instance being concerned is minimized, such that highly reliable superpoint correspondences can be extracted. The superpoint correspondences are then extended to instance candidates at the fine level according to the instance masks. At last, an efficient candidate selection and refinement algorithm is devised to obtain the final registrations. Extensive experiments on three public benchmarks demonstrate the efficacy of our approach. In particular, MIRETR outperforms the state of the arts by 16.6 points on F1 score on the challenging ROBI benchmark. Code and models are available at https://github.com/zhiyuanYU134/MIRETR.

One-shot imitation learning (OSIL) is to learn an imitator agent that can execute multiple tasks with only a single demonstration. In real-world scenario, the environment is dynamic, e.g., unexpected changes can occur after demonstration. Thus, achieving generalization of the imitator agent is crucial as agents would inevitably face situations unseen in the provided demonstrations. While traditional OSIL methods excel in relatively stationary settings, their adaptability to such unforeseen changes, which asking for a higher level of generalization ability for the imitator agents, is limited and rarely discussed. In this work, we present a new algorithm called Deep Demonstration Tracing (DDT). In DDT, we propose a demonstration transformer architecture to encourage agents to adaptively trace suitable states in demonstrations. Besides, it integrates OSIL into a meta-reinforcement-learning training paradigm, providing regularization for policies in unexpected situations. We evaluate DDT on a new navigation task suite and robotics tasks, demonstrating its superior performance over existing OSIL methods across all evaluated tasks in dynamic environments with unforeseen changes. The project page is in https://osil-ddt.github.io.

Synchronized dual-arm rearrangement is widely studied as a common scenario in industrial applications. It often faces scalability challenges due to the computational complexity of robotic arm rearrangement and the high-dimensional nature of dual-arm planning. To address these challenges, we formulated the problem as cooperative mTSP, a variant of mTSP where agents share cooperative costs, and utilized reinforcement learning for its solution. Our approach involved representing rearrangement tasks using a task state graph that captured spatial relationships and a cooperative cost matrix that provided details about action costs. Taking these representations as observations, we designed an attention-based network to effectively combine them and provide rational task scheduling. Furthermore, a cost predictor is also introduced to directly evaluate actions during both training and planning, significantly expediting the planning process. Our experimental results demonstrate that our approach outperforms existing methods in terms of both performance and planning efficiency.

This work focuses on the dual-arm object rearrangement problem abstracted from a realistic industrial scenario of Cartesian robots. The goal of this problem is to transfer all the objects from sources to targets with the minimum total completion time. To achieve the goal, the core idea is to develop an effective object-to-arm task assignment strategy for minimizing the cumulative task execution time and maximizing the dual-arm cooperation efficiency. One of the difficulties in the task assignment is the scalability problem. As the number of objects increases, the computation time of traditional offline-search-based methods grows strongly for computational complexity. Encouraged by the adaptability of reinforcement learning (RL) in long-sequence task decisions, we propose an online task assignment decision method based on RL, and the computation time of our method only increases linearly with the number of objects. Further, we design an attention-based network to model the dependencies between the input states during the whole task execution process to help find the most reasonable object-to-arm correspondence in each task assignment round. In the experimental part, we adapt some search-based methods to this specific setting and compare our method with them. Experimental result shows that our approach achieves outperformance over search-based methods in total execution time and computational efficiency, and also verifies the generalization of our method to different numbers of objects. In addition, we show the effectiveness of our method deployed on the real robot in the supplementary video.

Great progress has been made in rendering translucent materials in recent years, but automatically estimating parameters for heterogeneous materials such as jade and human skin remains a challenging task, often requiring specialized and expensive physical measurement devices. In this paper, we present a novel approach for estimating and transferring the parameters of heterogeneous translucent materials from a single 2D image to 3D models. Our method consists of four key steps: (1) An efficient viewpoint selection algorithm to minimize redundancy and ensure comprehensive coverage of the model. (2) Initializing a homogeneous translucent material to render initial images for translucent dataset. (3) Edit the rendered translucent images to update the translucent dataset. (4) Optimize the edited translucent results onto material parameters using inverse rendering techniques. Our approach offers a practical and accessible solution that overcomes the limitations of existing methods, which often rely on complex and costly specialized devices. We demonstrate the effectiveness and superiority of our proposed method through extensive experiments, showcasing its ability to transfer and edit high-quality heterogeneous translucent materials on 3D models, surpassing the results achieved by previous techniques in 3D scene editing.

Abstract With the emergence of large‐scale Text‐to‐Image(T2I) models and implicit 3D representations like Neural Radiance Fields (NeRF), many text‐driven generative editing methods based on NeRF have appeared. However, the implicit encoding of geometric and textural information poses challenges in accurately locating and controlling objects during editing. Recently, significant advancements have been made in the editing methods of 3D Gaussian Splatting, a real‐time rendering technology that relies on explicit representation. However, these methods still suffer from issues including inaccurate localization and limited manipulation over editing. To tackle these challenges, we propose GSEditPro, a novel 3D scene editing framework which allows users to perform various creative and precise editing using text prompts only. Leveraging the explicit nature of the 3D Gaussian distribution, we introduce an attention‐based progressive localization module to add semantic labels to each Gaussian during rendering. This enables precise localization on editing areas by classifying Gaussians based on their relevance to the editing prompts derived from cross‐attention layers of the T2I model. Furthermore, we present an innovative editing optimization method based on 3D Gaussian Splatting, obtaining stable and refined editing results through the guidance of Score Distillation Sampling and pseudo ground truth. We prove the efficacy of our method through extensive experiments.

Abstract Indoor scene point clouds exhibit diverse distributions and varying levels of sparsity, characterized by more intricate geometry and occlusion compared to outdoor scenes or individual objects. Despite recent advancements in 3D point cloud analysis introducing various network architectures, there remains a lack of frameworks tailored to the unique attributes of indoor scenarios. To address this, we propose DSGI‐Net, a novel indoor scene point cloud learning network that can be integrated into existing models. The key innovation of this work is selectively grouping more informative neighbor points in sparse regions and promoting semantic consistency of the local area where different instances are in proximity but belong to distinct categories. Furthermore, our method encodes both semantic and spatial relationships between points in local regions to reduce the loss of local geometric details. Extensive experiments on the ScanNetv2, SUN RGB‐D, and S3DIS indoor scene benchmarks demonstrate that our method is straightforward yet effective.

We introduce deformable interaction analogy (DINA) as a means to generate close interactions between two 3D objects. Given a single demo interaction between an anchor object (e.g. a hand) and a source object (e.g. a mug grasped by the hand), our goal is to generate many analogous 3D interactions between the same anchor object and various new target objects (e.g. a toy airplane), where the anchor object is allowed to be rigid or deformable. To this end, we optimize the pose or shape of the anchor object to adapt it to a new target object to mimic the demo. To facilitate the optimization, we advocate using interaction interface (ITF), defined by a set of points sampled on the anchor object, as a descriptive and robust interaction representation that is amenable to non-rigid deformation. We model similarity between interactions using ITF, while for interaction analogy, we transform the ITF, either rigidly or non-rigidly, to guide the feature matching to the reposing and deformation of the anchor object. Qualitative and quantitative experiments show that our ITF-guided deformable interaction analogy works surprisingly well even with simple distance features compared to variants of state-of-the-art methods that utilize more sophisticated interaction representations and feature learning from large datasets.

Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic grasping. Existing methods fail when the template and source images have different modalities, cluttered backgrounds, or weak textures. They also rarely consider geometric transformations via homographies, which commonly exist even for planar industrial parts. To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement. We use an edge-aware module to overcome the domain gap between the mask template and the grayscale image, allowing robust matching. An initial warp is estimated using coarse correspondences based on novel structure-aware information provided by transformers. This initial alignment is passed to a refinement network using references and aligned images to obtain sub-pixel level correspondences which are used to give the final geometric transformation. Extensive evaluation shows that our method to be significantly better than state-of-the-art methods and baselines, providing good generalization ability and visually plausible results even on unseen real data.

It is challenging to automatically explore an unknown 3D environment with a robot only equipped with depth sensors due to the limited field of view. We introduce THP, a tensor field-based framework for efficient environment exploration which can better utilize the encoded depth information through the geometric characteristics of tensor fields. Specifically, a corresponding tensor field is constructed incrementally and guides the robot to formulate optimal global exploration paths and a collision-free local movement strategy. Degenerate points generated during the exploration are adopted as anchors to formulate a hierarchical TSP for global path optimization. This novel strategy can help the robot avoid long-distance round trips more effectively while maintaining scanning completeness. Furthermore, the tensor field also enables a local movement strategy to avoid collision based on particle advection. As a result, the framework can eliminate massive, time-consuming recalculations of local movement paths. We have experimentally evaluate our method with a ground robot in 8 complex indoor scenes. Our method can on average achieve 14% better exploration efficiency and 21% better exploration completeness than state-of-the-art alternatives using LiDAR scans. Moreover, compared to similar methods, our method makes path decisions 39% faster due to our hierarchical exploration strategy.

Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any 3D annotations. The key idea of our approach is to design a trainable model that employs both incomplete 3D reconstructions and their corresponding source RGB-D images, fusing cross-domain features into volumetric embeddings to predict complete 3D geometry, color, and semantics with only 2D labeling which can be either manual or machine-generated. Our key technical innovation is to leverage differentiable rendering of color and semantics to bridge 2D observations and unknown 3D space, using the observed RGB images and 2D semantics as supervision, respectively. We additionally develop a learning pipeline and corresponding method to enable learning from imperfect predicted 2D labels, which could be additionally acquired by synthesizing in an augmented set of virtual training views complementing the original real captures, enabling more efficient self-supervision loop for semantics. As a result, our end-to-end trainable solution jointly addresses geometry completion, colorization, and semantic mapping from limited RGB-D images, without relying on any 3D ground-truth information. Our method achieves state-of-the-art performance of semantic scene completion on two large-scale benchmark datasets MatterPort3D and ScanNet, surpasses baselines even with costly 3D annotations in predicting both geometry and semantics. To our knowledge, our method is also the first 2D-driven method addressing completion and semantic segmentation of real-world 3D scans simultaneously.

The design and analysis of computer-aided design (CAD) sketches play a crucial role in industrial product design, primarily involving CAD primitives and their interprimitive constraints. To address challenges related to error accumulation in autoregressive models and the complexities associated with self-supervised model design for this task, we propose a two-stage network framework. This framework consists of a primitive network and a constraint network, transforming the sketch analysis task into a set prediction problem to enhance the effective handling of primitives and constraints. By decoupling target types from parameters, the model gains increased flexibility and optimization while reducing complexity. In addition, the constraint network incorporates a pointer module to explicitly indicate the relationship between constraint parameters and primitive indices, enhancing interpretability and performance. Qualitative and quantitative analyzes on two publicly available datasets demonstrate the superiority of this method.

Learning-based edge detection has hereunto been strongly supervised with pixel-wise annotations which are tedious to obtain manually. We study the problem of self-training edge detection, leveraging the untapped wealth of large-scale unlabeled image datasets. We design a self-supervised framework with multilayer regularization and self-teaching. In particular, we impose a consistency regularization which enforces the outputs from each of the multiple layers to be consistent for the input image and its perturbed counterpart. We adopt L0-smoothing as the "perturbation" to encourage edge prediction lying on salient boundaries following the cluster assumption in self-supervised learning. Meanwhile, the network is trained with multilayer supervision by pseudo labels which are initialized with Canny edges and then iteratively refined by the network as the training proceeds. The regularization and self-teaching together attain a good balance of precision and recall, leading to a significant performance boost over supervised methods, with lightweight refinement on the target dataset. Through extensive experiments, our method demonstrates strong cross-dataset generality and can improve the original performance of edge detectors after self-training and fine-tuning.

Learning-based surface reconstruction based on unsigned distance functions (UDF) has many advantages such as handling open surfaces. We propose SuperUDF, a self-supervised UDF learning which exploits a learned geometry prior for efficient training and a novel regularization for robustness to sparse sampling. The core idea of SuperUDF draws inspiration from the classical surface approximation operator of locally optimal projection (LOP). The key insight is that if the UDF is estimated correctly, the 3D points should be locally projected onto the underlying surface following the gradient of the UDF. Based on that, a number of inductive biases on UDF geometry and a pre-learned geometry prior are devised to learn UDF estimation efficiently. A novel regularization loss is proposed to make SuperUDF robust to sparse sampling. Furthermore, we also contribute a learning-based mesh extraction from the estimated UDFs. Extensive evaluations demonstrate that SuperUDF outperforms the state of the arts on several public datasets in terms of both quality and efficiency. Code will be released after accteptance.

Monocular depth estimation is a challenging problem on which deep neural networks have demonstrated great potential. However, depth maps predicted by existing deep models usually lack fine-grained details due to convolution operations and down-samplings in networks. We find that increasing input resolution is helpful to preserve more local details while the estimation at low resolution is more accurate globally. Therefore, we propose a novel depth map fusion module to combine the advantages of estimations with multi-resolution inputs. Instead of merging the low- and high-resolution estimations equally, we adopt the core idea of Poisson fusion, trying to implant the gradient domain of high-resolution depth into the low-resolution depth. While classic Poisson fusion requires a fusion mask as supervision, we propose a self-supervised framework based on guided image filtering. We demonstrate that this gradient-based composition performs much better at noisy immunity, compared with the state-of-the-art depth map fusion method. Our lightweight depth fusion is one-shot and runs in real-time, making it 80X faster than a state-of-the-art depth fusion method. Quantitative evaluations demonstrate that the proposed method can be integrated into many fully convolutional monocular depth estimation backbones with a significant performance boost, leading to state-of-the-art results of detail enhancement on depth maps. Codes are released at https://github.com/yuinsky/gradient-based-depth-map-fusion.

We study the problem of outlier correspondence pruning for non-rigid point cloud registration. In rigid registration, spatial consistency has been a commonly used criterion to discriminate outliers from inliers. It measures the compatibility of two correspondences by the discrepancy between the respective distances in two point clouds. However, spatial consistency no longer holds in non-rigid cases and outlier rejection for non-rigid registration has not been well studied. In this work, we propose Graph-based Spatial Consistency Network (GraphSCNet) to filter outliers for non-rigid registration. Our method is based on the fact that non-rigid deformations are usually locally rigid, or local shape preserving. We first design a local spatial consistency measure over the deformation graph of the point cloud, which evaluates the spatial compatibility only between the correspondences in the vicinity of a graph node. An attention-based non-rigid correspondence embedding module is then devised to learn a robust representation of non-rigid correspondences from local spatial consistency. Despite its simplicity, GraphSCNet effectively improves the quality of the putative correspondences and attains state-of-the-art performance on three challenging benchmarks. Our code and models are available at https://github.com/qinzheng93/GraphSCNet.

An ideal point cloud registration framework should have superior accuracy, acceptable efficiency, and strong generalizability: However, this is highly challenging since existing registration techniques are either not accurate enough, far from efficient, or generalized poorly. It remains an open question that how to achieve a satisfying balance between this three key elements. In this paper, we propose BUFFER, a point cloud registration method for balancing accuracy, efficiency, and generalizability. The key to our approach is to take advantage of both point-wise and patch-wise techniques, while overcoming the inherent drawbacks simultaneously. Different from a simple combination of existing methods, each component of our network has been carefully crafted to tackle specific issues. Specifically, a Point-wise Learner is first introduced to enhance computational efficiency by predicting keypoints and improving the representation capacity of features by estimating point orientations, a Patch-wise Embedder which leverages a lightweight local feature learner is then deployed to extract efficient and general patch features. Additionally, an Inliers Generator which combines simple neural layers and general features is presented to search inlier correspondences. Extensive experiments on real-world scenarios demonstrate that our method achieves the best of both worlds in accuracy, efficiency, and generalization. In particular, our method not only reaches the highest success rate on unseen domains, but also is almost 30 times faster than the strong baselines specializing in generalization. Code is available at https://github.com/aosheng1996/BUFFER.

We study the problem of reconstructing 3D feature curves of an object from a set of calibrated multi-view images. To do so, we learn a neural implicit field representing the density distribution of 3D edges which we refer to as Neural Edge Field (NEF). Inspired by NeRF [20], NEF is optimized with a view-based rendering loss where a 2D edge map is rendered at a given view and is compared to the ground-truth edge map extracted from the image of that view. The rendering-based differentiable optimization of NEF fully exploits 2D edge detection, without needing a supervision of 3D edges, a 3D geometric operator or cross-view edge correspondence. Several technical designs are devised to ensure learning a range-limited and view-independent NEF for robust edge extraction. The final parametric 3D curves are extracted from NEF with an iterative optimization method. On our benchmark with synthetic data, we demonstrate that NEF outperforms existing state-of-the-art methods on all metrics. Project page: https://yunfan1202.github.io/NEF/.

We present a learning-based approach to relight a single image of Lambertian and low-frequency specular objects. Our method enables inserting objects from photographs into new scenes and relighting them under the new environment lighting, which is essential for AR applications. To relight the object, we solve both inverse rendering and re-rendering. To resolve the ill-posed inverse rendering, we propose a weakly-supervised method by a low-rank constraint. To facilitate the weakly-supervised training, we contribute Relit, a large-scale (750K images) dataset of videos with aligned objects under changing illuminations. For re-rendering, we propose a differentiable specular rendering layer to render low-frequency non-Lambertian materials under various illuminations of spherical harmonics. The whole pipeline is end-to-end and efficient, allowing for a mobile app implementation of AR object insertion. Extensive evaluations demonstrate that our method achieves state-of-the-art performance. Project page: https://renjiaoyi.github.io/relighting/.

Object goal navigation (ObjectNav) in unseen environments is a fundamental task for Embodied AI. Agents in existing works learn ObjectNav policies based on 2D maps, scene graphs, or image sequences. Considering this task happens in 3D space, a 3D-aware agent can advance its ObjectNav capability via learning from fine-grained spatial information. However, leveraging 3D scene representation can be prohibitively unpractical for policy learning in this floor-level task, due to low sample efficiency and expensive computational cost. In this work, we propose a framework for the challenging 3D-aware ObjectNav based on two straightforward sub-policies. The two sub-polices, namely corner-guided exploration policy and category-aware identification policy, simultaneously perform by utilizing online fused 3D points as observation. Through extensive experiments, we show that this framework can dramatically improve the performance in ObjectNav through learning from 3D scene representation. Our framework achieves the best performance among all modular-based methods on the Matterport3D and Gibson datasets, while requiring (up to 30x) less computational cost for training. The code will be released to benefit the community.11Homepage: https://pku-epic.github.io/3D-Aware-ObjectNav/

The commonly adopted detect-then-match approach to registration finds difficulties in the cross-modality cases due to the incompatible keypoint detection and inconsistent feature description. We propose, 2D3D-MATR, a detection-free method for accurate and robust registration between images and point clouds. Our method adopts a coarse-to-fine pipeline where it first computes coarse correspondences between downsampled patches of the input image and the point cloud and then extends them to form dense correspondences between pixels and points within the patch region. The coarse-level patch matching is based on transformer which jointly learns global contextual constraints with self-attention and cross-modality correlations with cross-attention. To resolve the scale ambiguity in patch matching, we construct a multi-scale pyramid for each image patch and learn to find for each point patch the best matching image patch at a proper resolution level. Extensive experiments on two public benchmarks demonstrate that 2D3D-MATR outperforms the previous state-of-the-art P2-Net by around 20 percentage points on inlier ratio and over 10 points on registration recall. Our code and models are available at https://github.com/minhaolee/2D3DMATR.

3D plane recovery from a single image can usually be divided into several subtasks of plane detection, segmentation, parameter estimation and possibly depth estimation. Previous works tend to solve it by either extending the RCNN-based segmentation network or the dense pixel embedding-based clustering framework. However, none of them tried to integrate above related subtasks into a unified framework but treated them separately and sequentially, which we suspect is potentially a main source of performance limitation for existing approaches. Motivated by this finding and the success of query-based learning in enriching reasoning among semantic entities, in this paper, we propose PlaneRecTR, a Transformer-based architecture, which for the first time unifies all subtasks related to single-view plane recovery with a single compact model. Extensive quantitative and qualitative experiments demonstrate that our proposed unified learning achieves mutual benefits across subtasks, obtaining a new state-of-the-art performance on public ScanNet and NYUv2-Plane datasets. Codes are available at https://github.com/SJingjia/PlaneRecTR.

Most learning-based approaches to category-level 6D pose estimation are design around normalized object coordinate space (NOCS). While being successful, NOCS-based methods become inaccurate and less robust when handling objects of a category containing significant intra-category shape variations. This is because the object coordinates induced by global and rigid alignment of objects are semantically incoherent, making the coordinate regression hard to learn and generalize. We propose Semantically-aware Object Coordinate Space (SOCS) built by warping-and-aligning the objects guided by a sparse set of keypoints with semantically meaningful correspondence. SOCS is semantically coherent: Any point on the surface of a object can be mapped to a semantically meaningful location in SOCS, allowing for accurate pose and size estimation under large shape variations. To learn effective coordinate regression to SOCS, we propose a novel multi-scale coordinatebased attention network. Evaluations demonstrate that our method is easy to train, well-generalizing for large intracategory shape variations and robust to inter-object occlusions. Code is provided at: https://github.com/wanboyan/SOCS.

We introduce NIFT, Neural Interaction Field and Template, a descriptive and robust interaction representation of object manipulations to facilitate imitation learning. Given a few object manipulation demos, NIFT guides the generation of the interaction imitation for a new object instance by matching the Neural Interaction Template (NIT) extracted from the demos in the target Neural Interaction Field (NIF) defined for the new object. Specifically, the NIF is a neural field that encodes the relationship between each spatial point and a given object, where the relative position is defined by a spherical distance function rather than occupancies or signed distances, which are commonly adopted by conventional neural fields but less informative. For a given demo interaction, the corresponding NIT is defined by a set of spatial points sampled in the demo NIF with associated neural features. To better capture the interaction, the points are sampled on the Interaction Bisector Surface (IBS), which consists of points that are equidistant to the two interacting objects and has been used extensively for interaction representation. With both point selection and pointwise features defined for better interaction encoding, NIT effectively guides the feature matching in the NIFs of the new object instances such that the relative poses are optimized to realize the manipulation while imitating the demo interactions. Experiments show that our NIFT solution outperforms state-of-the-art imitation learning methods for object manipulation and generalizes better to objects from new categories.

Good proposal initials are critical for 3D object detection applications. However, due to the significant geometry variation of indoor scenes, incomplete and noisy proposals are inevitable in most cases. Mining feature information among these “bad” proposals may mislead the detection. Contrastive learning provides a feasible way for representing proposals, which can align complete and incomplete/noisy proposals in feature space. The aligned feature space can help us build robust 3D representation even if bad proposals are given. Therefore, we devise a new contrast learning framework for indoor 3D object detection, called EFECL, that learns robust 3D representations by contrastive learning of proposals on two different levels. Specifically, we optimize both instance-level and category-level contrasts to align features by capturing instance-specific characteristics and semantic-aware common patterns. Furthermore, we propose an enhanced feature aggregation module to extract more general and informative features for contrastive learning. Evaluations on ScanNet V2 and SUN RGB-D benchmarks demonstrate the generalizability and effectiveness of our method, and our method can achieve 12.3% and 7.3% improvements on both datasets over the benchmark alternatives. The code and models are publicly available at https://github.com/YaraDuan/EFECL .

The point pair feature (PPF) is widely used for 6D pose estimation. In this paper, we propose an efficient 6D pose estimation method based on the PPF framework. We introduce a well-targeted down-sampling strategy that focuses on edge areas for efficient feature extraction for complex geometry. A pose hypothesis validation approach is proposed to resolve ambiguity due to symmetry by calculating the edge matching degree. We perform evaluations on two challenging datasets and one real-world collected dataset, demonstrating the superiority of our method for pose estimation for geometrically complex, occluded, symmetrical objects. We further validate our method by applying it to simulated punctures.

We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods have shown great potential through bypassing the detection of repeatable keypoints which is difficult to do especially in low-overlap scenarios. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer, or GeoTransformer for short, to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it invariant to rigid transformation and robust in low-overlap cases. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration. Extensive experiments on rich benchmarks encompassing indoor, outdoor, synthetic, multiway and non-rigid demonstrate the efficacy of GeoTransformer. Notably, our method improves the inlier ratio by 18 ∼ 31 percentage points and the registration recall by over 7 points on the challenging 3DLoMatch benchmark.

Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range (depth) finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We devise a multi-task learning for better optimization convergence and depth accuracy. We found the monotonicity property of the SDFs along each ray greatly benefits the depth estimation. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods, achieving an overall reconstruction score of 0.33 mm on DTU and an F-score of 59.48% on Tanks & Temples. It is able to produce high-quality depth estimation and point cloud reconstruction in challenging scenarios such as objects/scenes with non-textured surface, severe occlusion, and highly varying depth range. Further, we propose RayMVSNet++ to enhance contextual feature aggregation for each ray through designing an attentional gating unit to select semantically relevant neighboring rays within the local frustum around that ray. This improves the performance on datasets with more challenging examples (e.g., low-quality images caused by poor lighting conditions or motion blur). RayMVSNet++ achieves state-of-the-art performance on the ScanNet dataset. In particular, it attains an AbsRel of 0.058m and produces accurate results on the two subsets of textureless regions and large depth variation.

3D symmetry detection is a fundamental problem in computer vision and graphics. Most prior works detect symmetry when the object model is fully known, few studies symmetry detection on objects with partial observation, such as single RGB-D images. Recent work addresses the problem of detecting symmetries from incomplete data with a deep neural network by leveraging the dense and accurate symmetry annotations. However, due to the tedious labeling process, full symmetry annotations are not always practically available. In this work, we present a 3D symmetry detection approach to detect symmetry from single-view RGB-D images without using symmetry supervision. The key idea is to train the network in a weakly-supervised learning manner to complete the shape based on the predicted symmetry such that the completed shape be similar to existing plausible shapes. To achieve this, we first propose a discriminative variational autoencoder to learn the shape prior in order to determine whether a 3D shape is plausible or not. Based on the learned shape prior, a symmetry detection network is present to predict symmetries that produce shapes with high shape plausibility when completed based on those symmetries. Moreover, to facilitate end-to-end network training and multiple symmetry detection, we introduce a new symmetry parametrization for the learning-based symmetry estimation of both reflectional and rotational symmetry. The proposed approach, coupled symmetry detection with shape completion, essentially learns the symmetry-aware shape prior, facilitating more accurate and robust symmetry detection. Experiments demonstrate that the proposed method is capable of detecting reflectional and rotational symmetries accurately, and shows good generality in challenging scenarios, such as objects with heavy occlusion and scanning noise. Moreover, it achieves state-of-the-art performance, improving the F1-score over the existing supervised learning method by 2%-11% on the ShapeNet and ScanNet datasets.

Learning-based edge detection usually suffers from predicting thick edges. Through extensive quantitative study with a new edge crispness measure, we find that noisy human-labeled edges are the main cause of thick predictions. Based on this observation, we advocate that more attention should be paid on label quality than on model design to achieve crisp edge detection. To this end, we propose an effective Canny-guided refinement of human-labeled edges whose result can be used to train crisp edge detectors. Essentially, it seeks for a subset of over-detected Canny edges that best align human labels. We show that several existing edge detectors can be turned into a crisp edge detector through training on our refined edge maps. Experiments demonstrate that deep models trained with refined edges achieve significant performance boost of crispness from 17.4% to 30.6%. With the PiDiNet backbone, our method improves ODS and OIS by 12.2% and 12.6% on the Multicue dataset, respectively, without relying on non-maximal suppression. We further conduct experiments and show the superiority of our crisp edge detection for optical flow estimation and image segmentation.

We introduce MIPS-Fusion, a robust and scalable online RGB-D reconstruction method based on a novel neural implicit representation - multi-implicit-submap. Different from existing neural RGB-D reconstruction methods lacking either flexibility with a single neural map or scalability due to extra storage of feature grids, we propose a pure neural representation tackling both difficulties with a divide-and-conquer design. In our method, neural submaps are incrementally allocated alongside the scanning trajectory and efficiently learned with local neural bundle adjustments. The submaps can be refined individually in a back-end optimization and optimized jointly to realize submap-level loop closure. Meanwhile, we propose a hybrid tracking approach combining randomized and gradient-based pose optimizations. For the first time, randomized optimization is made possible in neural tracking with several key designs to the learning process, enabling efficient and robust tracking even under fast camera motions. The extensive evaluation demonstrates that our method attains higher reconstruction quality than the state of the arts for large-scale scenes and under fast camera motions.

We study the problem of learning online packing skills for irregular 3D shapes , which is arguably the most challenging setting of bin packing problems. The goal is to consecutively move a sequence of 3D objects with arbitrary shapes into a designated container with only partial observations of the object sequence. We take physical realizability into account, involving physics dynamics and constraints of a placement. The packing policy should understand the 3D geometry of the object to be packed and make effective decisions to accommodate it in the container in a physically realizable way. We propose a Reinforcement Learning (RL) pipeline to learn the policy. The complex irregular geometry and imperfect object placement together lead to huge solution space. Direct training in such space is prohibitively data intensive. We instead propose a theoretically provable method for candidate action generation to reduce the action space of RL and the learning burden. A parameterized policy is then learned to select the best placement from the candidates. Equipped with an efficient method of asynchronous RL acceleration and a data preparation process of simulation-ready training sequences, a mature packing policy can be trained in a physics-based environment within 48 hours. Through extensive evaluation on a variety of real-life shape datasets and comparisons with state-of-the-art baselines, we demonstrate that our method outperforms the best-performing baseline on all datasets by at least 12.8% in terms of packing utility. We also release our datasets and source code to support further research in this direction. 1

High-dimensional nonlinear state estimation is at the heart of inertial-aided navigation systems (INS). Traditional methods usually rely on good initialization and find difficulty in handling large interframe transformations due to fast camera motion. We opt to tackle these challenges by solving the depth inertial odometry (DIO) problem with random optimization. To address the exponentially increased amount of candidate states sampled for the high-dimensional state space, we propose a highly efficient variant of random optimization based on the idea of active subspace. Our method identifies the active dimensions, which contribute most significantly to the decrease of the cost function in each iteration, and samples candidate states only within the corresponding subspace. This allows us to efficiently explore the 18D state space of DIO and achieve good optimality by sampling and evaluating only thousands of candidate states. Experiments show that our method attains highly robust and accurate DIO under fast camera motions and low light conditions, without needing a slow-motion warm-up for initialization.

Multi-view subspace clustering (MVSC) optimally integrates multiple graph structure information to improve clustering performance. Recently, many anchor-based variants are proposed to reduce the computational complexity of MVSC. Though achieving considerable acceleration, we observe that most of them adopt fixed anchor points separating from the subsequential anchor graph construction, which may adversely affect the clustering performance. In addition, post-processing is required to generate discrete clustering labels with additional time consumption. To address these issues, we propose a scalable and parameter-free MVSC method to directly output the clustering labels with optimal anchor graph, termed as Efficient One-pass Multi-view Subspace Clustering with Consensus Anchors (EOMSC-CA). Specially, we combine anchor learning and graph construction into a uniform framework to boost clustering performance. Meanwhile, by imposing a graph connectivity constraint, our algorithm directly outputs the clustering labels without any post-processing procedures as previous methods do. Our proposed EOMSC-CA is proven to be linear complexity respecting to the data size. The superiority of our EOMSC-CA over the effectiveness and efficiency is demonstrated by extensive experiments. Our code is publicly available at https://github.com/Tracesource/EOMSC-CA.

Multiple kernel clustering aims to seek an appropriate combination of base kernels to mine inherent non-linear information for optimal clustering. Late fusion algorithms generate base partitions independently and integrate them in the following clustering procedure, improving the overall efficiency. However, the separate base partition generation leads to inadequate negotiation with the clustering procedure and a great loss of beneficial information in corresponding kernel matrices, which negatively affects the clustering performance. To address this issue, we propose a novel algorithm, termed as Fusion Multiple Kernel k-means (FMKKM), which unifies base partition learning and late fusion clustering into one single objective function, and adopts early fusion technique to capture more sufficient information in kernel matrices. Specifically, the early fusion helps base partitions keep more beneficial kernel details, and the base partitions learning further guides the generation of consensus partition in the late fusion stage, while the late fusion provides positive feedback on two former procedures. The close collaboration of three procedures results in a promising performance improvement. Subsequently, an alternate optimization method with promising convergence is developed to solve the resultant optimization problem. Comprehensive experimental results demonstrate that our proposed algorithm achieves state-of-the-art performance on multiple public datasets, validating its effectiveness. The code of this work is publicly available at https://github.com/ethan-yizhang/Fusion-Multiple-Kernel-K-means.

We introduce Displacement Aware Relation Module (DisARM), a novel neural network module for enhancing the performance of 3D object detection in point cloud scenes. The core idea is extracting the most principal contextual information is critical for detection while the target is incomplete or featureless. We find that relations between proposals provide a good representation to describe the context. However, adopting relations between all the object or patch proposals for detection is inefficient, and an imbalanced combination of local and global relations brings extra noise that could mislead the training. Rather than working with all relations, we find that training with relations only between the most representative ones, or an-chors, can significantly boost the detection performance. Good anchors should be semantic-aware with no ambiguity and able to describe the whole layout of a scene with no redundancy. To find the anchors, we first perform a preliminary relation anchor module with an objectness-aware sampling approach and then devise a displacement based module for weighing the relation importance for better utilization of contextual information. This lightweight relation module leads to significantly higher accuracy of object instance detection when being plugged into the state-of-the-art detectors. Evaluations on the public benchmarks of real-world scenes show that our method achieves the state-of-the-art performance on both SUN RGB-D and Scan-Net V2. The code and models are publicly available at https://github.com/YaraDuan/DisARM.

Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences. However, since weak supervision cannot distinguish the losses caused by the detection and description steps, directly conducting weakly supervised learning within a joint training describe-then-detect pipeline suffers limited performance. In this paper, we propose a decoupled training describe-then-detect pipeline tailored for weakly supervised local feature learning. Within our pipeline, the detection step is decoupled from the description step and postponed until discriminative and robust descriptors are learned. In addition, we introduce a line-to-window search strategy to explicitly use the camera pose information for better descriptor learning. Extensive experiments show that our method, namely PoSFeat (Camera Pose Supervised Feature), outperforms previous fully and weakly supervised methods and achieves state-of-the-art performance on a wide range of downstream task.

We introduce RIM-Net, a neural network which learns recursive implicit fields for unsupervised inference of hierarchical shape structures. Our network recursively decomposes an input 3D shape into two parts, resulting in a binary tree hierarchy. Each level of the tree corresponds to an assembly of shape parts, represented as implicit functions, to reconstruct the input shape. At each node of the tree, simultaneous feature decoding and shape decomposition are carried out by their respective feature and part decoders, with weight sharing across the same hierarchy level. As an implicit field decoder, the part decoder is designed to decompose a sub-shape, via a two-way branched reconstruction, where each branch predicts a set of parameters defining a Gaussian to serve as a local point distribution for shape reconstruction. With reconstruction losses accounted for at each hierarchy level and a decomposition loss at each node, our network training does not require any ground-truth segmentations, let alone hierarchies. Through extensive experiments and comparisons to state-of-the-art alternatives, we demonstrate the quality, consistency, and interpretability of hierarchical structural inference by RIM-Net.

We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods bypass the detection of repeatable keypoints which is difficult in low-overlap scenarios, showing great potential in registration. They seek correspondences over down-sampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it robust in low-overlap cases and invariant to rigid transformation. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration. Our method improves the inlier ratio by 17∼30 percentage points and the registration recall by over 7 points on the challenging 3DLoMatch benchmark. Our code and models are available at https://github.com/qinzheng93/GeoTransformer.

Learning-based multi-view stereo (MVS) has by far cen-tered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Differentfrom most existing works dedicated to adaptive re-finement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range (depth) finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequen-tial prediction of aID implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We also devise a multi-task learning for better optimization convergence and depth accuracy. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods, achieving overall reconstruction score of 0.33mm on DTU andf-score of59.48% on Tanks & Temples.

Relation contexts have been proved to be useful for many challenging vision tasks. In the field of 3D object detection, previous methods have been taking the advantage of context encoding, graph embedding, or explicit relation reasoning to extract relation contexts. However, there exist inevitably redundant relation contexts due to noisy or low-quality proposals. In fact, invalid relation contexts usually indicate underlying scene misunderstanding and ambiguity, which may, on the contrary, reduce the performance in complex scenes. Inspired by recent attention mechanism like Transformer, we propose a novel 3D attention-based relation module (ARM3D). It encompasses object-aware relation reasoning to extract pair-wise relation contexts among qualified proposals and an attention module to distribute attention weights towards different relation contexts. In this way, ARM3D can take full advantage of the useful relation contexts and filter those less relevant or even confusing contexts, which mitigates the ambiguity in detection. We have evaluated the effectiveness of ARM3D by plugging it into several state-of-the-art 3D object detectors and showing more accurate and robust detection results. Extensive experiments show the capability and generalization of ARM3D on 3D object detection. Our source code is available at https://github.com/lanlan96/ARM3D .

Autonomous 3D acquisition of outdoor environments poses special challenges. Different from indoor scenes, where the room space is delineated by clear boundaries and separations (e.g., walls and furniture), an outdoor environment is spacious and unbounded (thinking of a campus). Therefore, unlike for indoor scenes where the scanning effort is mainly devoted to the discovery of boundary surfaces, scanning an open and unbounded area requires actively delimiting the extent of scanning region and dynamically planning a traverse path within that region. Thus, for outdoor scenes, we formulate the planning of an energy-efficient autonomous scanning through a discrete-continuous optimization of robot scanning paths. The discrete optimization computes a topological map, through solving an online traveling sales problem (Online TSP), which determines the scanning goals and paths on-the-fly. The dynamic goals are determined as a collection of visit sites with high reward of visibility-to-unknown. A visit graph is constructed via connecting the visit sites with edges weighted by traversing cost. This topological map evolves as the robot scans via deleting outdated sites that are either visited or become rewardless and inserting newly discovered ones. The continuous part optimizes the traverse paths geometrically between two neighboring visit sites via maximizing the information gain of scanning along the paths. The discrete and continuous processes alternate until the traverse cost of the current graph exceeds the remaining energy capacity of the robot. Our approach is evaluated with both synthetic and field tests, demonstrating its effectiveness and advantages over alternatives.

Wrapping objects using ropes is a common practice in our daily life. However, it is difficult to design and tie ropes on a 3D object with complex topology and geometry features while ensuring wrapping security and easy operation. In this article, we propose to compute a rope net that can tightly wrap around various 3D shapes. Our computed rope net not only immobilizes the object but also maintains the load balance during lifting. Based on the key observation that if every knot of the net has four adjacent curve edges, then only a single rope is needed to construct the entire net. We reformulate the rope net computation problem into a constrained curve network optimization. We propose a discrete-continuous optimization approach, where the topological constraints are satisfied in the discrete phase and the geometrical goals are achieved in the continuous stage. We also develop a hoist planning to pick anchor points so that the rope net equally distributes the load during hoisting. Furthermore, we simulate the wrapping process and use it to guide the physical rope net construction process. We demonstrate the effectiveness of our method on 3D objects with varying geometric and topological complexity. In addition, we conduct physical experiments to demonstrate the practicability of our method.

We approach the problem of high-DOF reaching-and-grasping via learning joint planning of grasp and motion with deep reinforcement learning. To resolve the sample efficiency issue in learning the high-dimensional and complex control of dexterous grasping, we propose an effective representation of grasping state characterizing the spatial interaction between the gripper and the target object. To represent gripper-object interaction, we adopt Interaction Bisector Surface (IBS) which is the Voronoi diagram between two close by 3D geometric objects and has been successfully applied in characterizing spatial relations between 3D objects. We found that IBS is surprisingly effective as a state representation since it well informs the finegrained control of each finger with spatial relation against the target object. This novel grasp representation, together with several technical contributions including a fast IBS approximation, a novel vector-based reward and an effective training strategy, facilitate learning a strong control model of high-DOF grasping with good sample efficiency, dynamic adaptability, and cross-category generality. Experiments show that it generates high-quality dexterous grasp for complex shapes with smooth grasping motions. Code and data for this paper are at https://github.com/qijinshe/IBS-Grasping.

We solve a challenging yet practically useful variant of 3D Bin Packing Problem (3D-BPP). In our problem, the agent has limited information about the items to be packed into a single bin, and an item must be packed immediately after its arrival without buffering or readjusting. The item's placement also subjects to the constraints of order dependence and physical stability. We formulate this online 3D-BPP as a constrained Markov decision process (CMDP). To solve the problem, we propose an effective and easy-to-implement constrained deep reinforcement learning (DRL) method under the actor-critic framework. In particular, we introduce a prediction-and-projection scheme: The agent first predicts a feasibility mask for the placement actions as an auxiliary task and then uses the mask to modulate the action probabilities output by the actor during training. Such supervision and projection facilitate the agent to learn feasible policies very efficiently. Our method can be easily extended to handle lookahead items, multi-bin packing, and item re-orienting. We have conducted extensive evaluation showing that the learned policy significantly outperforms the state-of-the-art methods. A preliminary user study even suggests that our method might attain a human-level performance.

Learning-based 3D shape segmentation is usually formulated as a semantic labeling problem, assuming that all parts of training shapes are annotated with a given set of tags. This assumption, however, is impractical for learning fine-grained segmentation. Although most off-the-shelf CAD models are, by construction, composed of fine-grained parts, they usually miss semantic tags and labeling those fine-grained parts is extremely tedious. We approach the problem with deep clustering, where the key idea is to learn part priors from a shape dataset with fine-grained segmentation but no part labels. Given point sampled 3D shapes, we model the clustering priors of points with a similarity matrix and achieve part segmentation through minimizing a novel low rank loss. To handle highly densely sampled point sets, we adopt a divide-and-conquer strategy. We partition the large point set into a number of blocks. Each block is segmented using a deep-clustering-based part prior network trained in a category-agnostic manner. We then train a graph convolution network to merge the segments of all blocks to form the final segmentation result. Our method is evaluated with a challenging benchmark of fine-grained segmentation, showing state-of-the-art performance.

We introduce the concept of geometric stability to the problem of 6D object pose estimation and propose to learn pose inference based on geometrically stable patches extracted from observed 3D point clouds. According to the theory of geometric stability analysis, a minimal set of three planar/cylindrical patches are geometrically stable and determine the full 6DoFs of the object pose. We train a deep neural network to regress 6D object pose based on geometrically stable patch groups via learning both intra-patch geometric features and inter-patch contextual features. A subnetwork is jointly trained to predict per-patch poses. This auxiliary task is a relaxation of the group pose prediction: A single patch cannot determine the full 6DoFs but is able to improve pose accuracy in its corresponding DoFs. Working with patch groups makes our method generalize well for random occlusion and unseen instances. The method is easily amenable to resolve symmetry ambiguities. Our method achieves the state-of-the-art results on public benchmarks compared not only to depth-only but also to RGBD methods. It also performs well in category-level pose estimation.

Online reconstruction based on RGB-D sequences has thus far been restrained to relatively slow camera motions (<1m/s). Under very fast camera motion (e.g., 3m/s), the reconstruction can easily crumble even for the state-of-the-art methods. Fast motion brings two challenges to depth fusion: 1) the high nonlinearity of camera pose optimization due to large inter-frame rotations and 2) the lack of reliably trackable features due to motion blur. We propose to tackle the difficulties of fast-motion camera tracking in the absence of inertial measurements using random optimization, in particular, the Particle Filter Optimization (PFO). To surmount the computation-intensive particle sampling and update in standard PFO, we propose to accelerate the randomized search via updating a particle swarm template (PST). PST is a set of particles pre-sampled uniformly within the unit sphere in the 6D space of camera pose. Through moving and rescaling the pre-sampled PST guided by swarm intelligence, our method is able to drive tens of thousands of particles to locate and cover a good local optimum extremely fast and robustly. The particles, representing candidate poses, are evaluated with a fitness function defined based on depth-model conformance. Therefore, our method, being depth-only and correspondence-free, mitigates the motion blur impediment as (ToF-based) depths are often resilient to motion blur. Thanks to the efficient template-based particle set evolution and the effective fitness function, our method attains good quality pose tracking under fast camera motion (up to 4m/s) in a realtime framerate without including loop closure or global pose optimization. Through extensive evaluations on public datasets of RGB-D sequences, especially on a newly proposed benchmark of fast camera motion, we demonstrate the significant advantage of our method over the state of the arts.

Learning powerful deep generative models for 3D shape synthesis is largely hindered by the difficulty in ensuring plausibility encompassing correct topology and reasonable geometry. Indeed, learning the distribution of plausible 3D shapes seems a daunting task for the holistic approaches, given the significant topological variations of 3D objects even within the same category. Enlightened by the fact that 3D shape structure is characterized as part composition and placement, we propose to model 3D shape variations with a part-aware deep generative network, coined as PAGENet. The network is composed of an array of per-part VAE-GANs, generating semantic parts composing a complete shape, followed by a part assembly module that estimates a transformation for each part to correlate and assemble them into a plausible structure. Through delegating the learning of part composition and part placement into separate networks, the difficulty of modeling structural variations of 3D shapes is greatly reduced. We demonstrate through both qualitative and quantitative evaluations that PAGENet generates 3D shapes with plausible, diverse and detailed structure, and show two applications, i.e., semantic shape segmentation and part-based shape editing.

We propose improving the cross-target and cross-scene generalization of visual navigation through learning an agent that is guided by conceiving the next observations it expects to see. This is achieved by learning a variational Bayesian model, called NeoNav, which generates the next expected observations (NEO) conditioned on the current observations of the agent and the target view. Our generative model is learned through optimizing a variational objective encompassing two key designs. First, the latent distribution is conditioned on current observations and the target view, leading to a model-based, target-driven navigation. Second, the latent space is modeled with a Mixture of Gaussians conditioned on the current observation and the next best action. Our use of mixture-of-posteriors prior effectively alleviates the issue of over-regularized latent space, thus significantly boosting the model generalization for new targets and in novel scenes. Moreover, the NEO generation models the forward dynamics of agent-environment interaction, which improves the quality of approximate inference and hence benefits data efficiency. We have conducted extensive evaluations on both real-world and synthetic benchmarks, and show that our model consistently outperforms the state-of-the-art models in terms of success rate, data efficiency, and generalization.

We introduce AdaCoSeg, a deep neural network architecture for adaptive co-segmentation of a set of 3D shapes represented as point clouds. Differently from the familiar single-instance segmentation problem, co-segmentation is intrinsically contextual: how a shape is segmented can vary depending on the set it is in. Hence, our network features an adaptive learning module to produce a consistent shape segmentation which adapts to a set. Specifically, given an input set of unsegmented shapes, we first employ an offline pre-trained part prior network to propose per-shape parts. Then the co-segmentation network iteratively and jointly optimizes the part labelings across the set subjected to a novel group consistency loss defined by matrix ranks. While the part prior network can be trained with noisy and inconsistently segmented shapes, the final output of AdaSeg is a consistent part labeling for the input set, with each shape segmented into up to (a user-specified) K parts. Overall, our method is weakly supervised, producing segmentations tailored to the test set, without consistent ground-truth segmentations. We show qualitative and quantitative results from AdaSeg and evaluate it via ablation studies and comparisons to state-of-the-art co-segmentation methods.

We present a novel approach to category-level 6D object pose and size estimation. To tackle intra-class shape variations, we learn canonical shape space (CASS), a unified representation for a large variety of instances of a certain object category. In particular, CASS is modeled as the latent space of a deep generative model of canonical 3D shapes with normalized pose. We train a variational auto-encoder (VAE) for generating 3D point clouds in the canonical space from an RGBD image. The VAE is trained in a cross-category fashion, exploiting the publicly available large 3D shape repositories. Since the 3D point cloud is generated in normalized pose (with actual size), the encoder of the VAE learns view-factorized RGBD embedding. It maps an RGBD image in arbitrary view into a pose-independent 3D shape representation. Object pose is then estimated via contrasting it with a pose-dependent feature of the input RGBD extracted with a separate deep neural networks. We integrate the learning of CASS and pose and size estimation into an end-to-end trainable network, achieving the state-of-the-art performance.

We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly. The input to our network is a 3D shape segmented into parts, where each part is first encoded into a feature representation using a part autoencoder. The core component of PQ-NET is a sequence-to-sequence or Seq2Seq autoencoder which encodes a sequence of part features into a latent vector of fixed size, and the decoder reconstructs the 3D shape, one part at a time, resulting in a sequential assembly. The latent space formed by the Seq2Seq encoder encodes both part structure and fine part geometry. The decoder can be adapted to perform several generative tasks including shape autoencoding, interpolation, novel shape generation, and single-view 3D reconstruction, where the generated shapes are all composed of meaningful parts.

In this paper, we address the 3D object detection task by capturing multi-level contextual information with the self-attention mechanism and multi-scale feature fusion. Most existing 3D object detection methods recognize objects individually, without giving any consideration on contextual information between these objects. Comparatively, we propose Multi-Level Context VoteNet (MLCVNet) to recognize 3D objects correlatively, building on the state-of-the-art VoteNet. We introduce three context modules into the voting and classifying stages of VoteNet to encode contextual information at different levels. Specifically, a Patch-to-Patch Context (PPC) module is employed to capture contextual information between the point patches, before voting for their corresponding object centroid points. Subsequently, an Object-to-Object Context (OOC) module is incorporated before the proposal and classification stage, to capture the contextual information between object candidates. Finally, a Global Scene Context (GSC) module is designed to learn the global scene context. We demonstrate these by capturing contextual information at patch, object and scene levels. Our method is an effective way to promote detection accuracy, achieving new state-of-the-art detection performance on challenging 3D object detection datasets, i.e., SUN RGBD and ScanNet. We also release our code at https://github.com/NUAAXQ/MLCVNet.

Online semantic 3D segmentation in company with real-time RGB-D reconstruction poses special challenges such as how to perform 3D convolution directly over the progressively fused 3D geometric data, and how to smartly fuse information from frame to frame. We propose a novel fusion-aware 3D point convolution which operates directly on the geometric surface being reconstructed and exploits effectively the inter-frame correlation for high-quality 3D feature learning. This is enabled by a dedicated dynamic data structure that organizes the online acquired point cloud with local-global trees. Globally, we compile the online reconstructed 3D points into an incrementally growing coordinate interval tree, enabling fast point insertion and neighborhood query. Locally, we maintain the neighborhood information for each point using an octree whose construction benefits from the fast query of the global tree. The local octrees facilitate efficient surface-aware point convolution. Both levels of trees update dynamically and help the 3D convolution effectively exploits the temporal coherence for effective information fusion across RGB-D frames.

We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data. We represent these edges as a collection of parametric curves (i.e.,~lines, circles, and B-splines). Accordingly, our deep neural network, coined PIE-NET, is trained for parametric inference of edges. The network relies on a "region proposal" architecture, where a first module proposes an over-complete collection of edge and corner points, and a second module ranks each proposal to decide whether it should be considered. We train and evaluate our method on the ABC dataset, a large dataset of CAD models, and compare our results to those produced by traditional (non-learning) processing pipelines, as well as a recent deep learning based edge detector (EC-NET). Our results significantly improve over the state-of-the-art from both a quantitative and qualitative standpoint.

Abstract 3D models of objects and scenes are critical to many academic disciplines and industrial applications. Of particular interest is the emerging opportunity for 3D graphics to serve artificial intelligence: computer vision systems can benefit from synthetically‐generated training data rendered from virtual 3D scenes, and robots can be trained to navigate in and interact with real‐world environments by first acquiring skills in simulated ones. One of the most promising ways to achieve this is by learning and applyinggenerative modelsof 3D content: computer programs that can synthesize new 3D shapes and scenes. To allow users to edit and manipulate the synthesized 3D content to achieve their goals, the generative model should also bestructure‐aware: it should express 3D shapes and scenes using abstractions that allow manipulation of their high‐level structure. This state‐of‐the‐art report surveys historical work and recent progress on learning structure‐aware generative models of 3D shapes and scenes. We present fundamental representations of 3D shape and scene geometry and structures, describe prominent methodologies including probabilistic models, deep generative models, program synthesis, and neural networks for structured data, and cover many recent methods for structure‐aware synthesis of 3D shapes and indoor scenes.

Abstract In order for the deep learning models to truly understand the 2D images for 3D geometry recovery, we argue that single‐view reconstruction should be learned in a part‐aware and weakly supervised manner. Such models lead to more profound interpretation of 2D images in which part‐based parsing and assembling are involved. To this end, we learn a deep neural network which takes a single‐view RGB image as input, and outputs a 3D shape in parts represented by 3D point clouds with an array of 3D part generators. In particular, we devise two levels of generative adversarial network (GAN) to generate shapes with both correct part shape and reasonable overall structure. To enable a self‐taught network training, we devise a differentiable projection module along with a self‐projection loss measuring the error between the shape projection and the input image. The training data in our method is unpaired between the 2D images and the 3D shapes with part decomposition. Through qualitative and quantitative evaluations on public datasets, we show that our method achieves good performance in part‐wise single‐view reconstruction.

We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image. Directly training a deep model for symmetry prediction, however, can quickly run into the issue of overfitting. We adopt a multi-task learning approach. Aside from symmetry axis prediction, our network is also trained to predict symmetry correspondences. In particular, given the 3D points present in the RGB-D image, our network outputs for each 3D point its symmetric counterpart corresponding to a specific predicted symmetry. In addition, our network is able to detect for a given shape multiple symmetries of different types. We also contribute a benchmark of 3D symmetry detection based on single-view RGB-D images. Extensive evaluation on the benchmark demonstrates the strong generalization ability of our method, in terms of high accuracy of both symmetry axis prediction and counterpart estimation. In particular, our method is robust in handling unseen object instances with large variation in shape, multi-symmetry composition, as well as novel object categories.

Indoor scenes exhibit rich hierarchical structure in 3D object layouts. Many tasks in 3D scene understanding can benefit from reasoning jointly about the hierarchical context of a scene, and the identities of objects. We present a variational denoising recursive autoencoder (VDRAE) that generates and iteratively refines a hierarchical representation of 3D object layouts, interleaving bottom-up encoding for context aggregation and top-down decoding for propagation. We train our VDRAE on large-scale 3D scene datasets to predict both instance-level segmentations and a 3D object detections from an over-segmentation of an input point cloud. We show that our VDRAE improves object detection performance on real-world 3D point cloud datasets compared to baselines from prior work.

For the task of mobility analysis of 3D shapes, we propose joint analysis for simultaneous motion part segmentation and motion attribute estimation, taking a single 3D model as input. The problem is significantly different from those tackled in the existing works which assume the availability of either a pre-existing shape segmentation or multiple 3D models in different motion states. To that end, we develop Shape2Motion which takes a single 3D point cloud as input, and jointly computes a mobility-oriented segmentation and the associated motion attributes. Shape2Motion is comprised of two deep neural networks designed for mobility proposal generation and mobility optimization, respectively. The key contribution of these networks is the novel motion-driven features and losses used in both motion part segmentation and motion attribute estimation. This is based on the observation that the movement of a functional part preserves the shape structure. We evaluate Shape2Motion with a newly proposed benchmark for mobility analysis of 3D shapes. Results demonstrate that our method achieves the state-of-the-art performance both in terms of motion part segmentation and motion attribute estimation.

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. These models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down recursive decomposition and develop the first deep learning model for hierarchical segmentation of 3D shapes, based on recursive neural networks. Starting from a full shape represented as a point cloud, our model performs recursive binary decomposition, where the decomposition network at all nodes in the hierarchy share weights. At each node, a node classifier is trained to determine the type (adjacency or symmetry) and stopping criteria of its decomposition. The features extracted in higher level nodes are recursively propagated to lower level ones. Thus, the meaningful decompositions in higher levels provide strong contextual cues constraining the segmentations in lower levels. Meanwhile, to increase the segmentation accuracy at each node, we enhance the recursive contextual feature with the shape feature extracted for the corresponding part. Our method segments a 3D shape in point cloud into an arbitrary number of parts, depending on the shape complexity, showing strong generality and flexibility. It achieves the state-of-the-art performance, both for fine-grained and semantic segmentation, on the public benchmark and a new benchmark of fine-grained segmentation proposed in this work. We also demonstrate its application for fine-grained part refinements in image-to-shape reconstruction.

We present a learning-based method for representing grasp poses of a high-DOF hand using neural networks. Due to redundancy in such high-DOF grippers, there exists a large number of equally effective grasp poses for a given target object, making it difficult for the neural network to find consistent grasp poses. We resolve this ambiguity by generating an augmented dataset that covers many possible grasps for each target object and train our neural networks using a consistency loss function to identify a one-to-one mapping from objects to grasp poses. We further enhance the quality of neural-network-predicted grasp poses using a collision loss function to avoid penetrations. We use an object dataset that combines the BigBIRD Database, the KIT Database, the YCB Database, and the Grasp Dataset to show that our method can generate high-DOF grasp poses with higher accuracy than supervised learning baselines. The quality of the grasp poses is on par with the groundtruth poses in the dataset. In addition, our method is robust and can handle noisy object models such as those constructed from multi-view depth images, allowing our method to be implemented on a 25-DOF Shadow Hand hardware platform.

Abstract We propose a novel approach to robot‐operated active understanding of unknown indoor scenes, based on online RGBD reconstruction with semantic segmentation. In our method, the exploratory robot scanning is both driven by and targeting at the recognition and segmentation of semantic objects from the scene. Our algorithm is built on top of a volumetric depth fusion framework and performs real‐time voxel‐based semantic labeling over the online reconstructed volume. The robot is guided by an online estimated discrete viewing score field (VSF) parameterized over the 3D space of 2D location and azimuth rotation. VSF stores for each grid the score of the corresponding view, which measures how much it reduces the uncertainty (entropy) of both geometric reconstruction and semantic labeling. Based on VSF, we select the next best views (NBV) as the target for each time step. We then jointly optimize the traverse path and camera trajectory between two adjacent NBVs, through maximizing the integral viewing score (information gain) along path and trajectory. Through extensive evaluation, we show that our method achieves efficient and accurate online scene parsing during exploratory scanning.

Active vision is inherently attention-driven: an agent actively selects views to attend in order to rapidly perform a vision task while improving its internal representation of the scene being observed. Inspired by the recent success of attention-based models in 2D vision tasks based on single RGB images, we address multi-view depth-based active object recognition using an attention mechanism, by use of an end-to-end recurrent 3D attentional network. The architecture takes advantage of a recurrent neural network to store and update an internal representation. Our model, trained with 3D shape datasets, is able to iteratively attend the best views targeting an object of interest for recognizing it. To realize 3D view selection, we derive a 3D spatial transformer network. It is differentiable, allowing training with backpropagation, and so achieving much faster convergence than the reinforcement learning employed by most existing attention-based models. Experiments show that our method, with only depth input, achieves state-of-the-art next-best-view performance both in terms of time taken and recognition accuracy.

Recently, network lasso has dawn much attention due to its remarkable performance on simultaneous clustering and optimization. However, it usually suffers from the imperfect data (noise, missing values, etc.), and yields sub-optimal solutions. The reason is that it finds the similar instances according to their features directly, which is usually impacted by the imperfect data, and thus returns sub-optimal results. In this paper, we propose triangle lasso to avoid its disadvantage for graph datasets. In a graph dataset, each instance is represented by a vertex. If two instances have many common adjacent vertices, they tend to become similar. Although some instances are profiled by the imperfect data, it is still able to find the similar counterparts. Furthermore, we develop an efficient algorithm based on Alternating Direction Method of Multipliers (ADMM) to obtain a moderately accurate solution. In addition, we present a dual method to obtain the accurate solution with the low additional time consumption. We demonstrate through extensive numerical experiments that triangle lasso is robust to the imperfect data. It usually yields a better performance than the state-of-the-art method when performing data analysis tasks in practical scenarios.

We present an autonomous scanning approach which allows multiple robots to perform collaborative scanning for dense 3D reconstruction of unknown indoor scenes. Our method plans scanning paths for several robots, allowing them to efficiently coordinate with each other such that the collective scanning coverage and reconstruction quality is maximized while the overall scanning effort is minimized. To this end, we define the problem as a dynamic task assignment and introduce a novel formulation based on Optimal Mass Transport (OMT). Given the currently scanned scene, a set of task views are extracted to cover scene regions which are either unknown or uncertain. These task views are assigned to the robots based on the OMT optimization. We then compute for each robot a smooth path over its assigned tasks by solving an approximate traveling salesman problem. In order to showcase our algorithm, we implement a multi-robot auto-scanning system. Since our method is computationally efficient, we can easily run it in real time on commodity hardware, and combine it with online RGB-D reconstruction approaches. In our results, we show several real-world examples of large indoor environments; in addition, we build a benchmark with a series of carefully designed metrics for quantitatively evaluating multi-robot autoscanning. Overall, we are able to demonstrate high-quality scanning results with respect to reconstruction quality and scanning efficiency, which significantly outperforms existing multi-robot exploration systems.

We present a generative neural network that enables us to generate plausible 3D indoor scenes in large quantities and varieties, easily and highly efficiently. Our key observation is that indoor scene structures are inherently hierarchical . Hence, our network is not convolutional; it is a recursive neural network, or RvNN. Using a dataset of annotated scene hierarchies, we train a variational recursive autoencoder , or RvNN-VAE, which performs scene object grouping during its encoding phase and scene generation during decoding. Specifically, a set of encoders are recursively applied to group 3D objects based on support, surround, and co-occurrence relations in a scene, encoding information about objects’ spatial properties, semantics , and relative positioning with respect to other objects in the hierarchy. By training a variational autoencoder (VAE), the resulting fixed-length codes roughly follow a Gaussian distribution. A novel 3D scene can be generated hierarchically by the decoder from a randomly sampled code from the learned distribution. We coin our method GRAINS, for Generative Recursive Autoencoders for INdoor Scenes. We demonstrate the capability of GRAINS to generate plausible and diverse 3D indoor scenes and compare with existing methods for 3D scene synthesis. We show applications of GRAINS including 3D scene modeling from 2D layouts, scene editing, and semantic scene segmentation via PointNet whose performance is boosted by the large quantity and variety of 3D scenes generated by our method.

Multi-view deep neural network is perhaps the most successful approach in 3D shape classification. However, the fusion of multi-view features based on max or average pooling lacks a view selection mechanism, limiting its application in, e.g., multi-view active object recognition by a robot. This paper presents VERAM, a view-enhanced recurrent attention model capable of actively selecting a sequence of views for highly accurate 3D shape classification. VERAM addresses an important issue commonly found in existing attention-based models, i.e., the unbalanced training of the subnetworks corresponding to next view estimation and shape classification. The classification subnetwork is easily overfitted while the view estimation one is usually poorly trained, leading to a suboptimal classification performance. This is surmounted by three essential view-enhancement strategies: 1) enhancing the information flow of gradient backpropagation for the view estimation subnetwork, 2) devising a highly informative reward function for the reinforcement training of view estimation and 3) formulating a novel loss function that explicitly circumvents view duplication. Taking grayscale image as input and AlexNet as CNN architecture, VERAM with 9 views achieves instance-level and class-level accuracy of 95.5 and 95.3 percent on ModelNet10, 93.7 and 92.1 percent on ModelNet40, both are the state-of-the-art performance under the same number of views.

In view-based 3D shape recognition, extracting discriminative visual representation of 3D shapes from projected images is considered the core problem. Projections with low discriminative ability can adversely influence the final 3D shape representation. Especially under the real situations with background clutter and object occlusion, the adverse effect is even more severe. To resolve this problem, we propose a novel deep neural network, View Discerning Network, which learns to judge the quality of views and adjust their contributions to the representation of shapes. In this network, a Score Generation Unit is devised to evaluate the quality of each projected image with score vectors. These score vectors are used to weight the image features and the weighted features perform much better than original features in 3D shape recognition task. In particular, we introduce two structures of Score Generation Unit, Channel-wise Score Unit and Part-wise Score Unit, to assess the quality of feature maps from different perspectives. Our network aggregates features and scores in an end-to-end framework, so that final shape descriptors are directly obtained from its output. Our experiments on ModelNet and ShapeNet Core55 show that View Discerning Network outperforms the state-of-the-arts in terms of the retrieval task, with excellent robustness against background clutter and object occlusion.

We propose to recover 3D shape structures from single RGB images, where structure refers to shape parts represented by cuboids and part relations encompassing connectivity and symmetry. Given a single 2D image with an object depicted, our goal is automatically recover a cuboid structure of the object parts as well as their mutual relations. We develop a convolutional-recursive auto-encoder comprised of structure parsing of a 2D image followed by structure recovering of a cuboid hierarchy. The encoder is achieved by a multi-scale convolutional network trained with the task of shape contour estimation, thereby learning to discern object structures in various forms and scales. The decoder fuses the features of the structure parsing network and the original image, and recursively decodes a hierarchy of cuboids. Since the decoder network is learned to recover part relations including connectivity and symmetry explicitly, the plausibility and generality of part structure recovery can be ensured. The two networks are jointly trained using the training data of contour-mask and cuboid-structure pairs. Such pairs are generated by rendering stock 3D CAD models coming with part segmentation. Our method achieves unprecedentedly faithful and detailed recovery of diverse 3D part structures from single-view 2D images. We demonstrate two applications of our method including structure-guided completion of 3D volumes reconstructed from single-view images and structure-aware interactive editing of 2D images.

We propose to synthesize feasible caging grasps for a target object through computing Caging Loops, a closed curve defined in the shape embedding space of the object. Different from the traditional methods, our approach decouples caging loops from the surface geometry of target objects through working in the embedding space. This enables us to synthesize caging loops encompassing multiple topological holes, instead of always tied with one specific handle which could be too small to be graspable by the robot gripper. Our method extracts caging loops through a topological analysis of the distance field defined for the target surface in the embedding space, based on a rigorous theoretical study on the relation between caging loops and the field topology. Due to the decoupling, our method can tolerate incomplete and noisy surface geometry of an unknown target object captured on-the-fly. We implemented our method with a robotic gripper and demonstrate through extensive experiments that our method can synthesize reliable grasps for objects with complex surface geometry and topology and in various scales.

To carry out autonomous 3D scanning and online reconstruction of unknown indoor scenes, one has to find a balance between global exploration of the entire scene and local scanning of the objects within it. In this work, we propose a novel approach, which provides object-aware guidance for autoscanning, for exploring, reconstructing, and understanding an unknown scene within one navigation pass. Our approach interleaves between object analysis to identify the next best object (NBO) for global exploration, and object-aware information gain analysis to plan the next best view (NBV) for local scanning. First, an objectness-based segmentation method is introduced to extract semantic objects from the current scene surface via a multi-class graph cuts minimization. Then, an object of interest (OOI) is identified as the NBO which the robot aims to visit and scan. The robot then conducts fine scanning on the OOI with views determined by the NBV strategy. When the OOI is recognized as a full object, it can be replaced by its most similar 3D model in a shape database. The algorithm iterates until all of the objects are recognized and reconstructed in the scene. Various experiments and comparisons have shown the feasibility of our proposed approach.

A majority of stock 3D models in modern shape repositories are assembled with many fine-grained components. The main cause of such data form is the component-wise modeling process widely practiced by human modelers. These modeling components thus inherently reflect some function-based shape decomposition the artist had in mind during modeling. On the other hand, modeling components represent an over-segmentation since a functional part is usually modeled as a multi-component assembly. Based on these observations, we advocate that labeled segmentation of stock 3D models should not overlook the modeling components and propose a learning solution to grouping and labeling of the fine-grained components. However, directly characterizing the shape of individual components for the purpose of labeling is unreliable, since they can be arbitrarily tiny and semantically meaningless. We propose to generate part hypotheses from the components based on a hierarchical grouping strategy, and perform labeling on those part groups instead of directly on the components. Part hypotheses are mid-level elements which are more probable to carry semantic information. A multi-scale 3D convolutional neural network is trained to extract context-aware features for the hypotheses. To accomplish a labeled segmentation of the whole shape, we formulate higher-order conditional random fields (CRFs) to infer an optimal label assignment for all components. Extensive experiments demonstrate that our method achieves significantly robust labeling results on raw 3D models from public shape repositories. Our work also contributes the first benchmark for component-wise labeling.

Capturing aerial videos with a quadrotor-mounted camera is a challenging creative task, as it requires the simultaneous control of the quadrotor's motion and the mounted camera's orientation. Letting the drone follow a pre-planned trajectory is a much more appealing option, and recent research has proposed a number of tools designed to automate the generation of feasible camera motion plans; however, these tools typically require the user to specify and edit the camera path, for example by providing a complete and ordered sequence of key viewpoints. In this paper, we propose a higher level tool designed to enable even novice users to easily capture compelling aerial videos of large-scale outdoor scenes. Using a coarse 2.5D model of a scene, the user is only expected to specify starting and ending viewpoints and designate a set of landmarks, with or without a particular order. Our system automatically generates a diverse set of candidate local camera moves for observing each landmark, which are collision-free, smooth, and adapted to the shape of the landmark. These moves are guided by a landmark-centric view quality field, which combines visual interest and frame composition. An optimal global camera trajectory is then constructed that chains together a sequence of local camera moves, by choosing one move for each landmark and connecting them with suitable transition trajectories. This task is formulated and solved as an instance of the Set Traveling Salesman Problem.

We present a semi-supervised co-analysis method for learning 3D shape styles from projected feature lines , achieving style patch localization with only weak supervision. Given a collection of 3D shapes spanning multiple object categories and styles, we perform style co-analysis over projected feature lines of each 3D shape and then back-project the learned style features onto the 3D shapes. Our core analysis pipeline starts with mid-level patch sampling and pre-selection of candidate style patches. Projective features are then encoded via patch convolution. Multi-view feature integration and style clustering are carried out under the framework of partially shared latent factor (PSLF) learning, a multi-view feature learning scheme. PSLF achieves effective multi-view feature fusion by distilling and exploiting consistent and complementary feature information from multiple views, while also selecting style patches from the candidates. Our style analysis approach supports both unsupervised and semi-supervised analysis. For the latter, our method accepts both user-specified shape labels and style-ranked triplets as clustering constraints. We demonstrate results from 3D shape style analysis and patch localization as well as improvements over state-of-the-art methods. We also present several applications enabled by our style analysis.

We introduce SCORES, a recursive neural network for shape composition. Our network takes as input sets of parts from two or more source 3D shapes and a rough initial placement of the parts. It outputs an optimized part structure for the composed shape, leading to high-quality geometry construction. A unique feature of our composition network is that it is not merely learning how to connect parts. Our goal is to produce a coherent and plausible 3D shape, despite large incompatibilities among the input parts. The network may significantly alter the geometry and structure of the input parts and synthesize a novel shape structure based on the inputs, while adding or removing parts to minimize a structure plausibility loss. We design SCORES as a recursive autoencoder network. During encoding, the input parts are recursively grouped to generate a root code. During synthesis, the root code is decoded, recursively, to produce a new, coherent part assembly. Assembled shape structures may be novel, with little global resemblance to training exemplars, yet have plausible substructures. SCORES therefore learns a hierarchical substructure shape prior based on per-node losses. It is trained on structured shapes from ShapeNet, and is applied iteratively to reduce the plausibility loss. We show results of shape composition from multiple sources over different categories of man-made shapes and compare with state-of-the-art alternatives, demonstrating that our network can significantly expand the range of composable shapes for assembly-based modeling.

Abstract We present a sparse optimization framework for extracting sparse shape priors from a collection of 3D models. Shape priors are defined as point‐set neighborhoods sampled from shape surfaces which convey important information encompassing normals and local shape characterization. A 3D shape model can be considered to be formed with a set of 3D local shape priors, while most of them are likely to have similar geometry. Our key observation is that the local priors extracted from a family of 3D shapes lie in a very low‐dimensional manifold. Consequently, a compact and informative subset of priors can be learned to efficiently encode all shapes of the same family. A comprehensive library of local shape priors is first built with the given collection of 3D models of the same family. We then formulate a global, sparse optimization problem which enforces selecting representative priors while minimizing the reconstruction error. To solve the optimization problem, we design an efficient solver based on the Augmented Lagrangian Multipliers method (ALM). Extensive experiments exhibit the power of our data‐driven sparse priors in elegantly solving several high‐level shape analysis applications and geometry processing tasks, such as shape retrieval, style analysis and symmetry detection.

Abstract Data‐driven methods serve an increasingly important role in discovering geometric, structural and semantic relationships between shapes. In contrast to traditional approaches that process shapes in isolation of each other, data‐driven methods aggregate information from 3D model collections to improve the analysis, modelling and editing of shapes. Data‐driven methods are also able to learn computational models that reason about properties and relationships of shapes without relying on hard‐coded rules or explicitly programmed instructions. Through reviewing the literature, we provide an overview of the main concepts and components of these methods, as well as discuss their application to classification, segmentation, matching, reconstruction, modelling and exploration, as well as scene analysis and synthesis. We conclude our report with ideas that can inspire future research in data‐driven shape analysis and processing.

Autonomous reconstruction of unknown scenes by a mobile robot inherently poses the question of balancing between exploration efficacy and reconstruction quality. We present a navigation-by-reconstruction approach to address this question, where moving paths of the robot are planned to account for both global efficiency for fast exploration and local smoothness to obtain high-quality scans. An RGB-D camera, attached to the robot arm, is dictated by the desired reconstruction quality as well as the movement of the robot itself. Our key idea is to harness a time-varying tensor field to guide robot movement, and then solve for 3D camera control under the constraint of the 2D robot moving path. The tensor field is updated in real time, conforming to the progressively reconstructed scene. We show that tensor fields are well suited for guiding autonomous scanning for two reasons: first, they contain sparse and controllable singularities that allow generating a locally smooth robot path, and second, their topological structure can be used for globally efficient path routing within a partially reconstructed scene. We have conducted numerous tests with a mobile robot, and demonstrate that our method leads to a smooth exploration and high-quality reconstruction of unknown indoor scenes.

We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures. Our key insight is that 3D shapes are effectively characterized by their hierarchical organization of parts, which reflects fundamental intra-shape relationships such as adjacency and symmetry. We develop a recursive neural net (RvNN) based autoencoder to map a flat, unlabeled, arbitrary part layout to a compact code. The code effectively captures hierarchical structures of man-made 3D objects of varying structural complexities despite being fixed-dimensional: an associated decoder maps a code back to a full hierarchy. The learned bidirectional mapping is further tuned using an adversarial setup to yield a generative model of plausible structures, from which novel structures can be sampled. Finally, our structure synthesis framework is augmented by a second trained module that produces fine-grained part geometry, conditioned on global and local structural context, leading to a full generative pipeline for 3D shapes. We demonstrate that without supervision, our network learns meaningful structural hierarchies adhering to perceptual grouping principles, produces compact codes which enable applications such as shape classification and partial matching, and supports shape synthesis and interpolation with significant variations in topology and geometry.

Many approaches to shape comparison and recognition start by establishing a shape correspondence. We "turn the table" and show that quality shape correspondences can be obtained by performing many shape recognition tasks. What is more, the method we develop computes a fine-grained, topology-varying part correspondence between two 3D shapes where the core evaluation mechanism only recognizes shapes globally. This is made possible by casting the part correspondence problem in a deformation-driven framework and relying on a data-driven "deformation energy" which rates visual similarity between deformed shapes and models from a shape repository. Our basic premise is that if a correspondence between two chairs (or airplanes, bicycles, etc.) is correct, then a reasonable deformation between the two chairs anchored on the correspondence ought to produce plausible , "chair-like" in-between shapes. Given two 3D shapes belonging to the same category, we perform a top-down, hierarchical search for part correspondences. For a candidate correspondence at each level of the search hierarchy, we deform one input shape into the other, while respecting the correspondence, and rate the correspondence based on how well the resulting deformed shapes resemble other shapes from ShapeNet belonging to the same category as the inputs. The resemblance, i.e., plausibility, is measured by comparing multi-view depth images over category-specific features learned for the various shape categories. We demonstrate clear improvements over state-of-the-art approaches through tests covering extensive sets of man-made models with rich geometric and topological variations.

LiDAR scanning has become a prevalent technique for digitalizing large-scale outdoor scenes. However, the raw LiDAR data often contain imperfections, e.g., missing large regions, anisotropy of sampling density, and contamination of noise and outliers, which are the major obstacles that hinder its more ambitious and higher level applications in digital city modeling. Observing that 3D urban scenes can be locally described with several low dimensional subspaces, we propose to locally classify the neighborhoods of the scans to model the substructures of the scenes. The key enabler is the adaptive kernel-scale scoring, filtering and clustering of substructures, making it possible to recover the local structures at all points simultaneously, even in the presence of severe data imperfections. Integrating the local analyses leads to robust shape detection from raw LiDAR data. On this basis, we develop several urban scene applications and verify them on a number of LiDAR scans with various complexities and styles, which demonstrates the effectiveness and robustness of our methods.

Abstract Several applications in shape modeling and exploration require identification and extraction of a 3D shape part matching a 2D sketch. We present CustomCut, an on‐demand part extraction algorithm. Given a sketched query, CustomCut automatically retrieves partially matching shapes from a database, identifies the region optimally matching the query in each shape, and extracts this region to produce a customized part that can be used in various modeling applications. In contrast to earlier work on sketch‐based retrieval of predefined parts, our approach can extract arbitrary parts from input shapes and does not rely on a prior segmentation into semantic components. The method is based on a novel data structure for fast retrieval of partial matches: the randomized compoundk‐NN graph built on multi‐view shape projections. We also employ a coarse‐to‐fine strategy to progressively refine part boundaries down to the level of individual faces. Experimental results indicate that our approach provides an intuitive and easy means to extract customized parts from a shape database, and significantly expands the design space for the user. We demonstrate several applications of our method to shape design and exploration.

Abstract Capturing the dynamics of articulated models is becoming increasingly important. Dynamics, better than geometry, encode the functional information of articulated objects such as humans, robots and mechanics. Acquired dynamic data is noisy, sparse, and temporarily incoherent. The latter property is especially prominent for analysis of dynamics. Thus, processing scanned dynamic data is typically an ill‐posed problem. We present an algorithm that robustly computes the joints representing the dynamics of a scanned articulated object. Our key idea is to by‐pass the reconstruction of the underlying surface geometry and directly solve for motion joints. To cope with the often‐times extremely incoherent scans, we propose a space‐time fitting‐and‐voting approach in the spirit of RANSAC. We assume a restricted set of articulated motions defined by a set of joints which we fit to the 4D dynamic data and measure their fitting quality. Thus, we repeatedly select random subsets and fit with joints, searching for an optimal candidate set of mobility parameters. Without having to reconstruct surfaces as intermediate means, our approach gains the advantage of being robust and efficient. Results demonstrate the ability to reconstruct dynamics of various articulated objects consisting of a wide range of complex and compound motions.

Abstract Consistent segmentation is to the center of many applications based on dynamic geometric data. Directly segmenting a raw 3D point cloud sequence is a challenging task due to the low data quality and large inter‐frame variation across the whole sequence. We propose alocal‐to‐globalapproach toco‐segmentpoint cloud sequences of articulated objects into near‐rigid moving parts. Our method starts from a per‐frame point clustering, derived from a robust voting‐based trajectory analysis. The local segments are then progressively propagated to the neighboring frames with a cut propagation operation, and further merged through all frames using a novelspace‐time segment groupingtechnqiue, leading to a globally consistent and compact segmentation of the entire articulated point cloud sequence. Such progressive propagating and merging, in both space and time dimensions, makes our co‐segmentation algorithm especially robust in handling noise, occlusions and pose/view variations that are usually associated with raw scan data.

We address the problem of autonomously exploring unknown objects in a scene by consecutive depth acquisitions. The goal is to reconstruct the scene while online identifying the objects from among a large collection of 3D shapes. Fine-grained shape identification demands a meticulous series of observations attending to varying views and parts of the object of interest. Inspired by the recent success of attention-based models for 2D recognition, we develop a 3D Attention Model that selects the best views to scan from, as well as the most informative regions in each view to focus on, to achieve efficient object recognition. The region-level attention leads to focus-driven features which are quite robust against object occlusion. The attention model, trained with the 3D shape collection, encodes the temporal dependencies among consecutive views with deep recurrent networks. This facilitates order-aware view planning accounting for robot movement cost. In achieving instance identification, the shape collection is organized into a hierarchy, associated with pre-trained hierarchical classifiers. The effectiveness of our method is demonstrated on an autonomous robot (PR) that explores a scene and identifies the objects to construct a 3D scene model.

Feature learning for 3D shapes is challenging due to the lack of natural paramterization for 3D surface models. We adopt the multi-view depth image representation and propose Multi-View Deep Extreme Learning Machine (MVD-ELM) to achieve fast and quality projective feature learning for 3D shapes. In contrast to existing multi-view learning approaches, our method ensures the feature maps learned for different views are mutually dependent via shared weights and in each layer, their unprojections together form a valid 3D reconstruction of the input 3D shape through using normalized convolution kernels. These lead to a more accurate 3D feature learning as shown by the encouraging results in several applications. Moreover, the 3D reconstruction property enables clear visualization of the learned features, which further demonstrates the meaningfulness of our feature learning.

Abstract Enhancing the self‐symmetry of a shape is of fundamental aesthetic virtue. In this paper, we are interested in recovering the aesthetics ofintrinsicreflection symmetries, where an asymmetric shape is symmetrized while keeping its general pose and perceived dynamics. The key challenge to intrinsic symmetrization is that the input shape has only approximate reflection symmetries, possibly far from perfect. The main premise of our work is that curve skeletons provide a concise and effective shape abstraction for analyzing approximate intrinsic symmetries as well as symmetrization. By measuring intrinsic distances over a curve skeleton for symmetry analysis, symmetrizing the skeleton, and then propagating the symmetrization from skeleton to shape, our approach to shape symmetrization isskeleton‐intrinsic. Specifically, given an input shape and an extracted curve skeleton, we introduce the notion of abackboneas the path in the skeleton graph about which a self‐matching of the input shape is optimal. We define an objective function for the reflective self‐matching and develop an algorithm based on genetic programming to solve the global search problem for the backbone. The extracted backbone then guides the symmetrization of the skeleton, which in turn, guides the symmetrization of the whole shape. We show numerous intrinsic symmetrization results of hand drawn sketches and artist‐modeled or reconstructed 3D shapes, as well as several applications of skeleton‐intrinsic symmetrization of shapes.

Detailed scanning of indoor scenes is tedious for humans. We propose autonomous scene scanning by a robot to relieve humans from such a laborious task. In an autonomous setting, detailed scene acquisition is inevitably coupled with scene analysis at the required level of detail. We develop a framework for object-level scene reconstruction coupled with object-centric scene analysis. As a result, the autoscanning and reconstruction will be object-aware , guided by the object analysis. The analysis is, in turn, gradually improved with progressively increased object-wise data fidelity. In realizing such a framework, we drive the robot to execute an iterative analyze-and-validate algorithm which interleaves between object analysis and guided validations. The object analysis incorporates online learning into a robust graph-cut based segmentation framework, achieving a global update of object-level segmentation based on the knowledge gained from robot-operated local validation. Based on the current analysis, the robot performs proactive validation over the scene with physical push and scan refinement, aiming at reducing the uncertainty of both object-level segmentation and object-wise reconstruction. We propose a joint entropy to measure such uncertainty based on segmentation confidence and reconstruction quality, and formulate the selection of validation actions as a maximum information gain problem. The output of our system is a reconstructed scene with both object extraction and object-wise geometry fidelity.

We present a deformation-driven approach to topology-varying 3D shape correspondence. In this paradigm, the best correspondence between two shapes is the one that results in a minimal-energy, possibly topology-varying, deformation that transforms one shape to conform to the other while respecting the correspondence. Our deformation model, called GeoTopo transform , allows both geometric and topological operations such as part split, duplication, and merging, leading to fine-grained and piecewise continuous correspondence results. The key ingredient of our correspondence scheme is a deformation energy that penalizes geometric distortion, encourages structure preservation, and simultaneously allows topology changes. This is accomplished by connecting shape parts using structural rods , which behave similarly to virtual springs but simultaneously allow the encoding of energies arising from geometric, structural, and topological shape variations. Driven by the combined deformation energy, an optimal shape correspondence is obtained via a pruned beam search. We demonstrate our deformation-driven correspondence scheme on extensive sets of man-made models with rich geometric and topological variation and compare the results to state-of-the-art approaches.

Abstract We propose a fast method for 3D shape segmentation and labeling via Extreme Learning Machine (ELM). Given a set of example shapes with labeled segmentation, we train an ELM classifier and use it to produce initial segmentation for test shapes. Based on the initial segmentation, we compute the final smooth segmentation through a graph‐cut optimization constrained by the super‐face boundaries obtained by over‐segmentation and the active contours computed from ELM segmentation. Experimental results show that our method achieves comparable results against the state‐of‐the‐arts, but reduces the training time by approximately two orders of magnitude, both for face‐level and super‐face‐level, making it scale well for large datasets. Based on such notable improvement, we demonstrate the application of our method for fast online sequential learning for 3D shape segmentation at face level, as well as realtime sequential learning at super‐face level.

We introduce focal points for characterizing, comparing, and organizing collections of complex and heterogeneous data and apply the concepts and algorithms developed to collections of 3D indoor scenes. We represent each scene by a graph of its constituent objects and define focal points as representative substructures in a scene collection. To organize a heterogeneous scene collection, we cluster the scenes based on a set of extracted focal points: scenes in a cluster are closely connected when viewed from the perspective of the representative focal points of that cluster. The key concept of representativity requires that the focal points occur frequently in the cluster and that they result in a compact cluster. Hence, the problem of focal point extraction is intermixed with the problem of clustering groups of scenes based on their representative focal points. We present a co-analysis algorithm which interleaves frequent pattern mining and subspace clustering to extract a set of contextual focal points which guide the clustering of the scene collection. We demonstrate advantages of focal-centric scene comparison and organization over existing approaches, particularly in dealing with hybrid scenes, scenes consisting of elements which suggest membership in different semantic categories.

We introduce an algorithm for generating novel 3D models via topology-varying shape blending. Given a source and a target shape, our method blends them topologically and geometrically, producing continuous series of in-betweens as new shape creations. The blending operations are defined on a spatio-structural graph composed of medial curves and sheets. Such a shape abstraction is structure-oriented, part-aware, and facilitates topology manipulations. Fundamental topological operations including split and merge are realized by allowing one-to-many correspondences between the source and the target. Multiple blending paths are sampled and presented in an interactive, exploratory tool for creative 3D modeling. We show a variety of topology-varying 3D shapes generated via continuous structural blending between man-made shapes exhibiting complex topological differences, in real time.

Abstract The emergence of laser/LiDAR sensors, reliable multi‐view stereo techniques and more recently consumer depth cameras have brought point clouds to the forefront as a data format useful for a number of applications. Unfortunately, the point data from those channels often incur imperfection, frequently contaminated with severe outliers and noise. This paper presents a robust consolidation algorithm for low‐quality point data from outdoor scenes, which essentially consists of two steps: 1) outliers filtering and 2) noise smoothing. We first design a connectivity‐based scheme to evaluate outlierness and thereby detect sparse outliers. Meanwhile, a clustering method is used to further remove small dense outliers. Both outlier removal methods are insensitive to the choice of the neighborhood size and the levels of outliers. Subsequently, we propose a novel approach to estimate normals for noisy points based on robust partial rankings, which is the basis of noise smoothing. Accordingly, a fast approach is exploited to smooth noise, while preserving sharp features. We evaluate the effectiveness of the proposed method on the point clouds from a variety of outdoor scenes.

Abstract Designing 3D objects from scratch is difficult, especially when the user intent is fuzzy and lacks a clear target form. We facilitate design by providing reference and inspiration from existing model contexts. We rethink model design as navigating through different possible combinations of part assemblies based on a large collection of pre‐segmented 3D models. We propose an interactive sketch‐to‐design system, where the user sketches prominent features of parts to combine. The sketched strokes are analysed individually, and more importantly, in context with the other parts to generate relevant shape suggestions via adesign galleryinterface. As a modelling session progresses and more parts get selected, contextual cues become increasingly dominant, and the model quickly converges to a final form. As a key enabler, we use pre‐learned part‐based contextual information to allow the user to quickly explore different combinations of parts. Our experiments demonstrate the effectiveness of our approach for efficiently designing new variations from existing shape collections.

ABSTRACT Arthroscopic surgeries, which are widely used for anterior cruciate ligament (ACL) reconstruction, not only require advanced hand–eye coordination but also involve complicated surgical procedure, necessitating simulation‐based training for surgeons. This paper describes a surgical procedure simulation system for the training of arthroscopic ACL reconstruction. Different from existing simulation‐based training systems for basic surgical skills, this system provides a complete simulation for the entire procedure of arthroscopic ACL reconstruction, involving operations such as puncturing, probing, incision, and drilling. In this system, we employ a linear elastic finite element method and position‐based dynamics for deformable modeling. Simplified vertex duplicating method and an implementation of real‐time Boolean operations are proposed for the topological change of tissue models involved in the incision simulation and tunnel construction. Two specially designed force feedback models are introduced for the haptic rendering of probing and drilling operations. By using these fast and stable simulation methods, this system is able to provide real‐time realistic graphical and haptic feedback to the user, making it efficient and practical for training purpose. Feedback from the surgeon trainees shows that this system is very effective in training not only for basic surgical skills but also for the complex surgical procedure. Copyright © 2012 John Wiley & Sons, Ltd.

We introduce an unsupervised co-hierarchical analysis of a set of shapes, aimed at discovering their hierarchical part structures and revealing relations between geometrically dissimilar yet functionally equivalent shape parts across the set. The core problem is that of representative co-selection . For each shape in the set, one representative hierarchy (tree) is selected from among many possible interpretations of the hierarchical structure of the shape. Collectively, the selected tree representatives maximize the within-cluster structural similarity among them. We develop an iterative algorithm for representative co-selection. At each step, a novel cluster-and-select scheme is applied to a set of candidate trees for all the shapes. The tree-to-tree distance for clustering caters to structural shape analysis by focusing on spatial arrangement of shape parts, rather than their geometric details. The final set of representative trees are unified to form a structural co-hierarchy. We demonstrate co-hierarchical analysis on families of man-made shapes exhibiting high degrees of geometric and finer-scale structural variabilities.

We present an algorithm for hierarchical and layered analysis of irregular facades, seeking a high-level understanding of facade structures. By introducing layering into the analysis, we no longer view a facade as a flat structure, but allow it to be structurally separated into depth layers, enabling more compact and natural interpretations of building facades. Computationally, we perform a symmetry-driven search for an optimal hierarchical decomposition defined by split and layering operations applied to an input facade. The objective is symmetry maximization , i.e., to maximize the sum of symmetry of the substructures resulting from recursive decomposition. To this end, we propose a novel integral symmetry measure, which behaves well at both ends of the symmetry spectrum by accounting for all partial symmetries in a discrete structure. Our analysis results in a structural representation, which can be utilized for structural editing and exploration of building facades.

We present an algorithm for multi-scale partial intrinsic symmetry detection over 2D and 3D shapes, where the scale of a symmetric region is defined by intrinsic distances between symmetric points over the region. To identify prominent symmetric regions which overlap and vary in form and scale, we decouple scale extraction and symmetry extraction by performing two levels of clustering. First, significant symmetry scales are identified by clustering sample point pairs from an input shape. Since different point pairs can share a common point, shape regions covered by points in different scale clusters can overlap. We introduce the symmetry scale matrix (SSM), where each entry estimates the likelihood two point pairs belong to symmetries at the same scale. The pair-to-pair symmetry affinity is computed based on a pair signature which encodes scales. We perform spectral clustering using the SSM to obtain the scale clusters. Then for all points belonging to the same scale cluster, we perform the second-level spectral clustering, based on a novel point-to-point symmetry affinity measure, to extract partial symmetries at that scale. We demonstrate our algorithm on complex shapes possessing rich symmetries at multiple scales.

We introduce set evolution as a means for creative 3D shape modeling, where an initial population of 3D models is evolved to produce generations of novel shapes. Part of the evolving set is presented to a user as a shape gallery to offer modeling suggestions. User preferences define the fitness for the evolution so that over time, the shape population will mainly consist of individuals with good fitness. However, to inspire the user's creativity, we must also keep the evolving set diverse. Hence the evolution is " fit and diverse ", drawing motivation from evolution theory. We introduce a novel part crossover operator which works at the finer-level part structures of the shapes, leading to significant variations and thus increased diversity in the evolved shape structures. Diversity is also achieved by explicitly compromising the fitness scores on a portion of the evolving population. We demonstrate the effectiveness of set evolution on man-made shapes. We show that selecting only models with high fitness leads to an elite population with low diversity. By keeping the population fit and diverse, the evolution can generate inspiring, and sometimes unexpected, shapes.

Abstract We introduce symmetry hierarchy of man‐made objects, a high‐level structural representation of a 3D model providing a symmetry‐induced, hierarchical organization of the model's constituent parts. Given an input mesh, we segment it into primitive parts and build an initial graph which encodes inter‐part symmetries and connectivity relations, as well as self‐symmetries in individual parts. The symmetry hierarchy is constructed from the initial graph via recursive graph contraction which either groups parts by symmetry or assembles connected sets of parts. The order of graph contraction is dictated by a set of precedence rules designed primarily to respect the law of symmetry in perceptual grouping and the principle of compactness of representation. We show that symmetry hierarchy naturally implies a hierarchical segmentation that is more meaningful than those produced by local geometric considerations. We also develop an application of symmetry hierarchies for structural shape editing.

We introduce an algorithm for 3D object modeling where the user draws creative inspiration from an object captured in a single photograph. Our method leverages the rich source of photographs for creative 3D modeling. However, with only a photo as a guide, creating a 3D model from scratch is a daunting task. We support the modeling process by utilizing an available set of 3D candidate models. Specifically, the user creates a digital 3D model as a geometric variation from a 3D candidate. Our modeling technique consists of two major steps. The first step is a user-guided image-space object segmentation to reveal the structure of the photographed object. The core step is the second one, in which a 3D candidate is automatically deformed to fit the photographed target under the guidance of silhouette correspondence. The set of candidate models have been pre-analyzed to possess useful high-level structural information, which is heavily utilized in both steps to compensate for the ill-posedness of the analysis and modeling problems based only on content in a single image. Equally important, the structural information is preserved by the geometric variation so that the final product is coherent with its inherited structural information readily usable for subsequent model refinement or processing.

We present an implicit approach for pair-wise non-rigid registration of moving and deforming objects. Shapes of interest are implicitly embedded in the 3D implicit vector space. In this implicit embedding space, registration is performed using a global-to-local framework. Firstly, a non-linear optimization functional defined on the vector distance function is used to find the global alignment between shapes. Secondly, an incremental cubic B-spline free form deformation is used to recover the non-rigid transformation parameters. Local non-rigid registration is posed in terms of minimising an energy functional, for which we give a closed-form linear system and solve it using an improved iterative Gauss-Seidel method. Our approach can consistently produce smooth and continuous registration fields, and correctly establish dense one-to-one correspondences. It can naturally deal with both open partial and closed shapes, and imperfect models with gaps and noise, through its use of the implicit vector representation. Experimental results on several datasets demonstrate the robustness of the proposed method.

We perform co-analysis of a set of man-made 3D objects to allow the creation of novel instances derived from the set. We analyze the objects at the part level and treat the anisotropic part scales as a shape style. The co-analysis then allows style transfer to synthesize new objects. The key to co-analysis is part correspondence, where a major challenge is the handling of large style variations and diverse geometric content in the shape set. We propose style-content separation as a means to address this challenge. Specifically, we define a correspondence-free style signature for style clustering. We show that confining analysis to within a style cluster facilitates tasks such as co-segmentation, content classification, and deformation-driven part correspondence. With part correspondence between each pair of shapes in the set, style transfer can be easily performed. We demonstrate our analysis and synthesis results on several sets of man-made objects with style and content variations.

Traditional texturing using a set of two dimensional image maps is an established and widespread practice. However, it is difficult to parameterize a model in texture space, particularly with representations such as implicit surfaces, subdivision surfaces, and very dense or detailed polygonal meshes. Based on an adaptive octree textures definition, this paper proposes a direct reverse-projecting pixel-level painting approach which has less storage requirements to general octree textures maps. In addition, it depends on texture lookup in the GPU, which particularly lookup faster than the non-GPU program.

The essence of a 3D shape can often be well captured by its salient feature curves. In this paper, we explore the use of salient curves in synthesizing intuitive, shape-revealing textures on surfaces. Our texture synthesis is guided by two principles: matching the direction of the texture patterns to those of the salient curves, and aligning the prominent feature lines in the texture to the salient curves exactly. We have observed that textures synthesized by these principles not only fit naturally to the surface geometry, but also visually reveal, even reinforce, the shape's essential characteristics. We call these feature-aligned shape texturing . Our technique is fully automatic, and introduces two novel technical components in vector-field-guided texture synthesis: an algorithm that orients the salient curves on a surface for constrained vector field generation, and a feature-to-feature texture optimization.

While many 3D objects exhibit various forms of global symmetries, prominent intrinsic symmetries which exist only on parts of an object are also well recognized. Such partial symmetries are often seen as more natural than a global one, even when the symmetric parts are under complex pose. We introduce an algorithm to extract partial intrinsic reflectional symmetries (PIRS) of a 3D shape. Given a closed 2-manifold mesh, we develop a voting scheme to obtain an intrinsic reflectional symmetry axis (IRSA) transform, which is a scalar field over the mesh that accentuates prominent IRSAs of the shape. We then extract a set of explicit IRSA curves on the shape based on a refined measure of local reflectional symmetry support along a curve. The iterative refinement procedure combines IRSA-induced region growing and region-constrained symmetry support refinement to improve accuracy and address potential issues arising from rotational symmetries in the shape. We show how the extracted IRSA curves can be incorporated into a conventional mesh segmentation scheme so that the implied symmetry cues can be utilized to obtain more meaningful results. We also demonstrate the use of IRSA curves for symmetry-driven part repair.

The effort of on-the-fly accessing 3D contents over the Internet has been done in recent years. And 3D streaming has been investigated to represent 3D models in the compact format and progressively transmit them on the limited-bandwidth and lossy channel. In the paper, an error resilient 3D mesh coding algorithm is presented, which employs an extended multiple quantization (EMQ) arithmetic coder method, inspired by the error-resilient JPEG 2000 image coding standards. With periodic arithmetic coder restarting and termination markers, the error resilient EMQ coder divides bit stream into little independent parts and enables basic transmission error containment. Furthermore, the EMQ coder has the intrinsic capacity of handling noise by using the maximum a posteriori (MAP) decoder. Experiments show that the method improves the mesh transmission quality in a simulated network environment.

Abstract In this paper, we propose a fast and stable method for 2D shape deformation based on rigid square matching. Our method utilizes uniform quadrangular control meshes for 2D shapes and tries to maintain the rigidity of each square in the control mesh during user manipulation. A rigid shape matching method is performed to find an optimal pure rotational transformation for each square in the control mesh. An iterative solver is proposed to compute the final deformation result for the entire control mesh by minimizing the difference between the deformed vertices and their counterparts in the neighboring rigid square. The deformation result on the 2D shape is as rigid as possible and the details of the shape are preserved well. As extensions, we present a shape‐aware splitting method to improve the deformation effect for coarse meshes and a simple sketch‐based clustering method for skeletal deformation. Experiments with various 2D shapes show that our method is efficient and easy to use, and can provide physically plausible result for shapes of objects in real world. Therefore, our shape deformation method is especially suitable for applications in cartoon character animation. Copyright © 2008 John Wiley & Sons, Ltd.