Multimodal Large Language Models (MLLMs) struggle with accurately capturing camera-object relations, especially for object orientation, camera viewpoint, and camera shots. This stems from the fact that existing MLLMs are trained on images with limited diverse camera-object relations and corresponding textual descriptions. To address this, we propose a synthetic generation pipeline to create large-scale 3D visual instruction datasets. Our framework takes 3D assets as input and uses rendering and diffusion-based image generation models to create photorealistic images preserving precise camera-object relations. Additionally, large language models (LLMs) are used to generate text prompts for guiding visual instruction tuning and controlling image generation. We create Ultimate3D, a dataset of 240K VQAs with precise camera-object annotations, and corresponding benchmark. MLLMs fine-tuned on our proposed dataset outperform commercial models by a large margin, achieving an average accuracy improvement of 33.4% on camera-object relation recognition tasks. Our code, dataset, and benchmark will contribute to broad MLLM applications.

Open-vocabulary 3D segmentation allows exploration of 3D environments using unrestricted natural language queries. Current approaches to open-vocabulary 3D instance segmentation largely concentrate on recognizing object-level instances but face difficulties when dealing with more fine-grained elements of a scene, such as object parts. Some previous work constructs hierarchical open-vocabulary 3D scene representations by geometric over-segmentation, which can’t identify parts with similar geometry. In this work, we introduce PS3, an approach to generate 3D part proposals from multi-view 2D masks. PS3 outperforms baselines that rely on geometric over-segmentation in scene-scale open-vocabulary 3D part segmentation.

We present iFusion, a novel 3D object reconstruction framework that requires only two views with unknown camera poses. While single-view reconstruction yields visually appealing results, it can deviate significantly from the actual object, especially on unseen sides. Additional views improve reconstruction fidelity but necessitate known camera poses. However, assuming the availability of pose may be unrealistic, and existing pose estimators fail in sparseview scenarios. To address this, we harness a pre-trained novel view synthesis diffusion model, which embeds implicit knowledge about the geometry and appearance of diverse objects. Our strategy unfolds in three steps: (1) We invert the diffusion model for camera pose estimation instead of synthesizing novel views. (2) The diffusion model is finetuned using provided views and estimated poses, turned into a novel view synthesizer tailored for the target object. (3) Leveraging registered views and the fine-tuned diffusion model, we reconstruct the 3D object. Experiments demonstrate strong performance in both pose estimation and novel view synthesis. Moreover, iFusion seamlessly integrates with various reconstruction methods and enhances them.

Recent advancements in 3D Large Multi-modal Models (3D-LMMs) have driven significant progress in 3D question answering. However, recent multi-frame Vision-Language Models (VLMs) demonstrate superior performance compared to 3D-LMMs on 3D question answering tasks, largely due to the greater scale and diversity of available 2D image data in contrast to the more limited 3D data. Multi-frame VLMs, although achieving superior performance, suffer from the difficulty of retaining all the detailed visual information in the 3D scene while limiting the number of visual tokens. Common methods such as token pooling, reduce visual token usage but often lead to information loss, impairing the model’s ability to preserve visual details essential for 3D question answering tasks. To address this, we propose voxel-based Dynamic Token Compression (DTC), which combines 3D spatial priors and visual semantics to achieve over 90% reduction in visual tokens usage for current multi-frame VLMs. Our method maintains performance comparable to state-of-the-art models on 3D question answering benchmarks including OpenEQA and ScanQA, demonstrating its effectiveness.

6D object pose estimation has shown strong generalizability to novel objects. However, existing methods often require either a complete, well-reconstructed 3D model or numerous reference images that fully cover the object. Estimating 6D poses from partial references, which capture only fragments of an object’s appearance and geometry, remains challenging. To address this, we propose UA-Pose, an uncertainty-aware approach for 6D object pose estimation and online object completion specifically designed for partial references. We assume access to either (1) a limited set of RGBD images with known poses or (2) a single 2D image. For the first case, we initialize a partial object 3D model based on the provided images and poses, while for the second, we use image-to-3D techniques to generate an initial object 3D model. Our method integrates uncertainty into the incomplete 3D model, distinguishing between seen and unseen regions. This uncertainty enables confidence assessment in pose estimation and guides an uncertainty-aware sampling strategy for online object completion, enhancing robustness in pose estimation accuracy and improving object completeness. We evaluate our method on the YCB-Video, YCBInEOAT, and HO3D datasets, including RGBD sequences of YCB objects manipulated by robots and human hands. Experimental results demonstrate significant performance improvements over existing methods, particularly when object observations are incomplete or partially captured. Project page: https://minfenli.github.io/UA-Pose/

In this paper, we present a novel algorithm for quantifying uncertainty and information gained within 3D Gaussian Splatting (3D-GS) through P-Optimality. While 3D-GS has proven to be a useful world model with high-quality rasterizations, it does not natively quantify uncertainty or information, posing a challenge for real-world applications such as 3D-GS SLAM. We propose to quantify information gain in 3D-GS by reformulating the problem through the lens of optimal experimental design, which is a classical solution widely used in literature. By restructuring information quantification of 3D-GS through optimal experimental design, we arrive at multiple solutions, of which T-Optimality and D-Optimality perform the best quantitatively and qualitatively as measured on two popular datasets. Additionally, we propose a block diagonal covariance approximation which provides a measure of correlation at the expense of a greater computation cost.

Unlike closed-vocabulary 3D instance segmentation that is often trained end-to-end, open-vocabulary 3D instance segmentation (OV-3DIS) often leverages vision-language models (VLMs) to generate 3D instance proposals and classify them. While various concepts have been proposed from existing research, we observe that these individual concepts are not mutually exclusive but complementary. In this paper, we propose a new state-of-the-art solution for OV-3DIS by carefully designing a recipe to combine the concepts together and refining them to address key challenges. Our solution follows the two-stage scheme: 3D proposal generation and instance classification. We employ robust 3D tracking-based proposal aggregation to generate 3D proposals and remove overlapped or partial proposals by iterative merging/removal. For the classification stage, we replace the standard CLIP model with Alpha-CLIP, which incorporates object masks as an alpha channel to reduce background noise and obtain object-centric representation. Additionally, we introduce the standardized maximum similarity (SMS) score to normalize text-to-proposal similarity, effectively filtering out false positives and boosting precision. Our framework achieves state-of-the-art performance on ScanNet200 and S3DIS across all AP and AR metrics, even surpassing an end-to-end closed-vocabulary method.

In this paper, we present a novel algorithm for probabilistically updating and rasterizing semantic maps within 3D Gaussian Splatting (3D-GS). Although previous methods have introduced algorithms which learn to rasterize features in 3D-GS for enhanced scene understanding, 3D-GS can fail without warning which presents a challenge for safety-critical robotic applications. To address this gap, we propose a method which advances the literature of continuous semantic mapping from voxels to ellipsoids, combining the precise structure of 3D-GS with the ability to quantify uncertainty of probabilistic robotic maps. Given a set of images, our algorithm performs a probabilistic semantic update directly on the 3D ellipsoids to obtain an expectation and variance through the use of conjugate priors. We also propose a probabilistic rasterization which returns per-pixel segmentation predictions with quantifiable uncertainty. We compare our method with similar probabilistic voxel-based methods to verify our extension to 3D ellipsoids, and perform ablation studies on uncertainty quantification and temporal smoothing.

3D object generation from a single unposed RGB image is essential for robotic perception, as reconstructing complete geometry and texture is essential for precise manipulation, grasping, and scene understanding, which is key for autonomous navigation and dexterous interaction. Recent advancements in image-to-3D employ Gaussian Splatting with pre-trained 2D or 3D diffusion models, but a disparity exists: 2D models generate high-fidelity textures yet lack geometric consistency, while 3D models ensure structural coherence but produce overly smooth textures. To address this, we introduce a two-stage frequency-based distillation loss integrated with Gaussian Splatting, leveraging geometric priors from a 3D diffusion model’s low-frequency spectrum for structural consistency and a 2D diffusion model’s high-frequency details for sharper textures. Our approach achieves state-of-the-art 3D reconstruction quality, significantly improving robotic perception pipelines. Additionally, we demonstrate the easy adaptability of our method for highly accurate object pose estimation and tracking, which is critical for precise robotic grasping, manipulation, and scene understanding. Additional results can be found in the supplementary file.

We introduce ET-Former, a novel end-to-end algorithm for semantic scene completion using a single monocular camera. Our approach generates a semantic occupancy map from single RGB observation while simultaneously providing uncertainty estimates for semantic predictions. By designing a triplane-based deformable attention mechanism, our approach improves geometric understanding of the scene than other SOTA approaches and reduces noise in semantic predictions. Additionally, through the use of a Conditional Variational AutoEncoder (CVAE), we estimate the uncertainties of these predictions. The generated semantic and uncertainty maps will help formulate navigation strategies that facilitate safe and permissible decision making in the future. Evaluated on the Semantic-KITTI dataset, ET-Former achieves the highest Intersection over Union (IoU) and mean IoU (mIoU) scores while maintaining the lowest GPU memory usage, surpassing state-of-the-art (SOTA) methods. It improves the SOTA scores of IoU from 44.71 to 51.49 and mIoU from 15.04 to 16.30 on SeamnticKITTI test, with a notably low training memory consumption of 10.9 GB, achieving at least a 25% reduction compared to previous methods. Project page: https://github.com/amazon-science/ET-Former.

Articulated 3D reconstruction has valuable applications in various domains, yet it remains costly and demands intensive work from domain experts. Recent advancements in template-free learning methods show promising results with monocular videos. Nevertheless, these approaches necessitate a comprehensive coverage of all viewpoints of the subject in the input video, thus limiting their applicability to casually captured videos from online sources. In this work, we study articulated 3D shape reconstruction from a single and casually captured Internet video, where the subject's view coverage is incomplete. We propose DreaMo that jointly performs shape reconstruction while solving the challenging low-coverage regions with view-conditioned diffusion prior and several tailored regularizations. In addition, we introduce a skeleton generation strategy to create human-interpretable skeletons from the learned neural bones and skinning weights without any predefined skeleton structures. We conduct our study on a self-collected internet video collection characterized by incomplete view coverage. DreaMo shows promising quality in novel-view rendering, detailed articulated shape reconstruction, and skeleton generation. Extensive qualitative and quantitative studies validate the efficacy of each proposed component, and show existing methods are unable to solve correct geometry due to the incomplete view coverage.

The field of indoor monocular 3D object detection is gaining significant attention, fueled by the increasing demand in VR/AR and robotic applications. However, its advancement is impeded by the limited availability and diversity of 3D training data, owing to the labor-intensive nature of 3D data collection and annotation processes. In this paper, we present V-MIND (Versatile Monocular INdoor Detector), which enhances the performance of in-door 3D detectors across a diverse set of object classes by harnessing publicly available large-scale 2D datasets. By leveraging well-established monocular depth estimation techniques and camera intrinsic predictors, we can generate 3D training data by converting large-scale 2D images into 3D point clouds and subsequently deriving pseudo 3D bounding boxes. To mitigate distance errors inherent in the converted point clouds, we introduce a novel 3D self-calibration loss for refining the pseudo 3D bounding boxes during training. Additionally, we propose a novel ambiguity loss to address the ambiguity that arises when introducing new classes from 2D datasets. Finally, through joint training with existing 3D datasets and pseudo 3D bounding boxes derived from 2D datasets, V-MIND achieves state-of-the-art object detection performance across a wide range of classes on the Omni3D indoor dataset.

We present uLayout, a unified model for estimating room layout geometries from both perspective and panoramic images, whereas traditional solutions require different model designs for each image type. The key idea of our solution is to unify both domains into the equirectangular projection, particularly, allocating perspective images into the most suitable latitude coordinate to effectively exploit both domains seamlessly. To address the Field-of-View (FoV) difference between the input domains, we design uLayout with a shared feature extractor with an extra 1D-Convolution layer to condition each domain input differently. This conditioning allows us to efficiently formulate a column-wise feature regression problem regardless of the FoV input. This simple yet effective approach achieves competitive performance with current state-of-the-art solutions and shows for the first time a single end-to-end model for both domains. Extensive experiments in the real-world datasets, LSUN, Matterport3D, PanoContext, and Stanford 2D-3D evidence the contribution of our approach. Code is available at https://github.com/JonathanLee112/uLayout

Machine learning models face generalization challenges when exposed to out-of-distribution (OOD) samples with unforeseen distribution shifts. Recent research reveals that for vision tasks, test-time adaptation employing diffusion models can achieve state-of-the-art accuracy improvements on OOD samples by generating domain-aligned samples without altering the model's weights. Unfortunately, those studies have primarily focused on pixel-level corruptions, thereby lacking the generalization to adapt to a broader range of OOD types. We introduce Generalized Diffusion Adaptation (GDA), a novel diffusion-based test-time adaptation method robust against diverse OOD types. Specifically, GDA iteratively guides the diffusion by applying a marginal entropy loss derived from the model, in conjunction with style and content preservation losses during the reverse sampling process. In other words, GDA considers the model's output behavior and the samples' semantic information as a whole, reducing ambiguity in downstream tasks. Evaluation across various model architectures and OOD benchmarks indicates that GDA consistently surpasses previous diffusion-based adaptation methods. Notably, it achieves the highest classification accuracy improvements, ranging from 4.4% to 5.02% on ImageNet-C and 2.5% to 7.4% on Rendition, Sketch, and Stylized benchmarks. This performance highlights GDA's generalization to a broader range of OOD benchmarks.

Inherent ambiguity in layout annotations poses significant challenges to developing accurate 360° room layout estimation models. To address this issue, we propose a novel Bi-Layout model capable of predicting two distinct layout types. One stops at ambiguous regions, while the other extends to encompass all visible areas. Our model employs two global context embeddings, where each embedding is designed to capture specific contextual information for each layout type. With our novel feature guidance module, the image feature retrieves relevant context from these embeddings, generating layout-aware features for precise bi-layout predictions. A unique property of our Bi-Layout model is its ability to inherently detect ambiguous regions by comparing the two predictions. To circumvent the need for manual correction of ambiguous annotations during testing, we also introduce a new metric for disambiguating ground truth layouts. Our method demonstrates superior performance on benchmark datasets, notably outperforming leading approaches. Specifically, on the MatterportLayout dataset, it improves 3DIoU from 81.70% to 82.57% across the full test set and notably from 54.80% to 59.97% in subsets with significant ambiguity.

We present a novel end-to-end algorithm (PoCo) for the indoor RGB-D place recognition task, aimed at identifying the most likely match for a given query frame within a reference database. The task presents inherent challenges attributed to the constrained field of view and limited range of perception sensors. We propose a new network architecture, which generalizes the recent Context of Clusters (CoCs) to extract global descriptors directly from the noisy point clouds through end-to-end learning. Moreover, we develop the architecture by integrating both color and geometric modalities into the point features to enhance the global descriptor representation. We conducted evaluations on public datasets ScanNet-PR and ARKit with 807 and 5047 scenarios, respectively. PoCo achieves SOTA performance: on ScanNet-PR, we achieve R@1 of 64.63%, a 5.7% improvement from the best-published result CGis (61.12%); on Arkit, we achieve R@1 of 45.12%, a 13.3% improvement from the best-published result CGis (39.82%). In addition, PoCo shows higher efficiency than CGis in inference time (1.75X-faster), and we demonstrate the effectiveness of PoCo in recognizing places within a real-world laboratory environment. Video: https://youtu.be/D8dObAeMiCw;

Large-scale pre-trained vision-language models (VLM) such as CLIP [32] have demonstrated noteworthy zero-shot classification capability, achieving 76.3% top-1 accuracy on ImageNet without seeing any examples. However, while applying CLIP to a downstream target domain, the presence of visual and text domain gaps and cross-modality misalignment can greatly impact the model performance. To address such challenges, we propose ReCLIP, a novel source-free domain adaptation method for VLMs, which does not require any source data or target labeled data. ReCLIP first learns a projection space to mitigate the misaligned visual-text embeddings and learns pseudo labels. Then, it deploys cross-modality self-training with the pseudo labels to update visual and text encoders, refine labels and reduce domain gaps and misalignment iteratively. With extensive experiments, we show that ReCLIP outperforms all the baselines significantly and improves the average accuracy of CLIP from 69.83% to 74.94% on 22 image classification benchmarks.

Although significant progress has been made in face recognition, demographic bias still exists in face recognition systems. For instance, it usually happens that the face recognition performance for a certain demographic group is lower than the others. In this paper, we propose MixFairFace framework to improve the fairness in face recognition models. First of all, we argue that the commonly used attribute-based fairness metric is not appropriate for face recognition. A face recognition system can only be considered fair while every person has a close performance. Hence, we propose a new evaluation protocol to fairly evaluate the fairness performance of different approaches. Different from previous approaches that require sensitive attribute labels such as race and gender for reducing the demographic bias, we aim at addressing the identity bias in face representation, i.e., the performance inconsistency between different identities, without the need for sensitive attribute labels. To this end, we propose MixFair Adapter to determine and reduce the identity bias of training samples. Our extensive experiments demonstrate that our MixFairFace approach achieves state-of-the-art fairness performance on all benchmark datasets.

We propose a Bidirectional Alignment for domain adaptive Detection with Transformers (BiADT) to improve cross domain object detection performance. Existing adversarial learning based methods use gradient reverse layer (GRL) to reduce the domain gap between the source and target domains in feature representations. Since different image parts and objects may exhibit various degrees of domain-specific characteristics, directly applying GRL on a global image or object representation may not be suitable. Our proposed BiADT explicitly estimates token-wise domain-invariant and domain-specific features in the image and object token sequences. BiADT has a novel deformable attention and self-attention, aimed at bi-directional domain alignment and mutual information minimization. These two objectives reduce the domain gap in domain-invariant representations, and simultaneously increase the distinctiveness of domain-specific features. Our experiments show that BiADT achieves very competitive performance to SOTA consistently on Cityscapes-to-FoggyCityscapes, Sim10K-to-Citiscapes and Cityscapes-to-BDD100K, outperforming the strong baseline, AQT, by 2.0, 2.1, and 2.4 in mAP50, respectively. The implementation is available at https://github.com/helq2612/biADT

We propose ImGeoNet, a multi-view image-based 3D object detection framework that models a 3D space by an image-induced geometry-aware voxel representation. Unlike previous methods which aggregate 2D features into 3D voxels without considering geometry, ImGeoNet learns to induce geometry from multi-view images to alleviate the confusion arising from voxels of free space, and during the inference phase, only images from multiple views are required. Besides, a powerful pre-trained 2D feature extractor can be leveraged by our representation, leading to a more robust performance. To evaluate the effectiveness of ImGeoNet, we conduct quantitative and qualitative experiments on three indoor datasets, namely ARKitScenes, ScanNetV2, and ScanNet200. The results demonstrate that ImGeoNet outperforms the current state-of-the-art multiview image-based method, ImVoxelNet, on all three datasets in terms of detection accuracy. In addition, ImGeoNet shows great data efficiency by achieving results comparable to ImVoxelNet with 100 views while utilizing only 40 views. Furthermore, our studies indicate that our proposed image-induced geometry-aware representation can enable image-based methods to attain superior detection accuracy than the seminal point cloud-based method, VoteNet, in two practical scenarios: (1) scenarios where point clouds are sparse and noisy, such as in ARKitScenes, and (2) scenarios involve diverse object classes, particularly classes of small objects, as in the case in ScanNet200. Project page: https://ttaoretw.github.io/imgeonet.

Aggregating information from features across different layers is essential for dense prediction models. Despite its limited expressiveness, vanilla feature concatenation dominates the choice of aggregation operations. In this paper, we introduce Attentive Feature Aggregation (AFA) to fuse different network layers with more expressive non-linear operations. AFA exploits both spatial and channel attention to compute weighted averages of the layer activations. Inspired by neural volume rendering, we further extend AFA with Scale-Space Rendering (SSR) to perform a late fusion of multi-scale predictions. AFA is applicable to a wide range of existing network designs. Our experiments show consistent and significant improvements on challenging semantic segmentation benchmarks, including Cityscapes and BDD100K at negligible computational and parameter overhead. In particular, AFA improves the performance of the Deep Layer Aggregation (DLA) model by nearly 6% mIoU on Cityscapes. Our experimental analyses show that AFA learns to progressively refine segmentation maps and improve boundary details, leading to new state-of-the-art results on boundary detection benchmarks on NYUDv2 and BSDS500.

A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform. The object association leverages quasi-dense similarity learning to identify objects in various poses and viewpoints with appearance cues only. After initial 2D association, we further utilize 3D bounding boxes depth-ordering heuristics for robust instance association and motion-based 3D trajectory prediction for re-identification of occluded vehicles. In the end, an LSTM-based object velocity learning module aggregates the long-term trajectory information for more accurate motion extrapolation. Experiments on our proposed simulation data and real-world benchmarks, including KITTI, nuScenes, and Waymo datasets, show that our tracking framework offers robust object association and tracking on urban-driving scenarios. On the Waymo Open benchmark, we establish the first camera-only baseline in the 3D tracking and 3D detection challenges. Our quasi-dense 3D tracking pipeline achieves impressive improvements on the nuScenes 3D tracking benchmark with near five times tracking accuracy of the best vision-only submission among all published methods.

Due to the rise of spherical cameras, monocular 360$^\circ$depth estimation becomes an important technique for many applications (e.g., autonomous systems). Thus, state-of-the-art frameworks for monocular 360$^\circ$depth estimation such as bi-projection fusion in BiFuse are proposed. To train such a framework, a large number of panoramas along with the corresponding depth ground truths captured by laser sensors are required, which highly increases the cost of data collection. Moreover, since such a data collection procedure is time-consuming, the scalability of extending these methods to different scenes becomes a challenge. To this end, self-training a network for monocular depth estimation from 360$^\circ$videos is one way to alleviate this issue. However, there are no existing frameworks that incorporate bi-projection fusion into the self-training scheme, which highly limits the self-supervised performance since bi-projection fusion can leverage information from different projection types. In this paper, we propose BiFuse++ to explore the combination of bi-projection fusion and the self-training scenario. To be specific, we propose a new fusion module and Contrast-Aware Photometric Loss to improve the performance of BiFuse and increase the stability of self-training on real-world videos. We conduct both supervised and self-supervised experiments on benchmark datasets and achieve state-of-the-art performance.

We present a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses. This task, which is often applied to novel view synthesis, is recently revolution-ized by Neural Radiance Field (NeRF) for its state-of-the-art quality and fiexibility. However, NeRF and its variants require a lengthy training time ranging from hours to days for a single scene. In contrast, our approach achieves NeRF-comparable quality and converges rapidly from scratch in less than 15 minutes with a single GPU. We adopt a representation consisting of a density voxel grid for scene geometry and a feature voxel grid with a shallow network for complex view-dependent appearance. Modeling with explicit and discretized volume representations is not new, but we propose two simple yet non-trivial techniques that contribute to fast convergence speed and high-quality output. First, we introduce the post-activation interpolation on voxel density, which is capable of producing sharp surfaces in lower grid resolution. Second, direct voxel density optimization is prone to suboptimal geometry solutions, so we robustify the optimization process by imposing several priors. Finally, evaluation on five inward-facing benchmarks shows that our method matches, if not surpasses, NeRF's quality, yet it only takes about 15 minutes to train from scratch for a new scene. Code: https://github.com/sunset1995/DirectVoxGO.

With the rapid development of artificial intelligence and autonomous driving technology, the demand for semiconductors is projected to rise substantially. However, the massive expansion of semiconductor manufacturing and the development of new technology will bring many defect wafers. If these defect wafers have not been correctly inspected, the ineffective semiconductor processing on these defect wafers will cause additional impact to our environment, such as excessive carbon dioxide emission and energy consumption. In this paper, we utilize the information processing advantages of quantum computing to promote the defect learning defect review (DLDR). We propose a classical-quantum hybrid algorithm for deep learning on near-term quantum processors. By tuning parameters implemented on it, quantum circuit driven by our framework learns a given DLDR task, include of wafer defect map classification, defect pattern classification, and hotspot detection. In addition, we explore parametrized quantum circuits with different expressibility and entangling capacities. These results can be used to build a future roadmap to develop circuit-based quantum deep learning for semiconductor defect detection.

We propose CLA-NeRF - a Category-Level Articulated Neural Radiance Field that can perform view synthesis, part segmentation, and articulated pose estimation. CLA-NeRF is trained at the object category level using no CAD models and no depth, but a set of RGB images with ground truth camera poses and part segments. During inference, it only takes a few RGB views (i.e., few-shot) of an unseen 3D object instance within the known category to infer the object part segmentation and the neural radiance field. Given an articulated pose as input, CLA-NeRF can perform articulation-aware volume rendering to generate the corresponding RGB image at any camera pose. Moreover, the articulated pose of an object can be estimated via inverse rendering. In our experiments, we evaluate the framework across five categories on both synthetic and real-world data. In all cases, our method shows realistic deformation results and accurate articulated pose estimation. We believe that both few-shot articulated object rendering and articulated pose estimation open doors for robots to perceive and interact with unseen articulated objects.

We present 360-MLC, a self-training method based on multi-view layout consistency for finetuning monocular room-layout models using unlabeled 360-images only. This can be valuable in practical scenarios where a pre-trained model needs to be adapted to a new data domain without using any ground truth annotations. Our simple yet effective assumption is that multiple layout estimations in the same scene must define a consistent geometry regardless of their camera positions. Based on this idea, we leverage a pre-trained model to project estimated layout boundaries from several camera views into the 3D world coordinate. Then, we re-project them back to the spherical coordinate and build a probability function, from which we sample the pseudo-labels for self-training. To handle unconfident pseudo-labels, we evaluate the variance in the re-projected boundaries as an uncertainty value to weight each pseudo-label in our loss function during training. In addition, since ground truth annotations are not available during training nor in testing, we leverage the entropy information in multiple layout estimations as a quantitative metric to measure the geometry consistency of the scene, allowing us to evaluate any layout estimator for hyper-parameter tuning, including model selection without ground truth annotations. Experimental results show that our solution achieves favorable performance against state-of-the-art methods when self-training from three publicly available source datasets to a unique, newly labeled dataset consisting of multi-view images of the same scenes.

Humans can master a new task within a few trials by drawing upon skills acquired through prior experience. To mimic this capability, hierarchical models combining primitive policies learned from prior tasks have been proposed. However, these methods fall short comparing to the human's range of transferability. We propose a method, which leverages the hierarchical structure to train the combination function and adapt the set of diverse primitive polices alternatively, to efficiently produce a range of complex behaviors on challenging new tasks. We also design two regularization terms to improve the diversity and utilization rate of the primitives in the pre-training phase. We demonstrate that our method outperforms other recent policy transfer methods by combining and adapting these reusable primitives in tasks with continuous action space. The experiment results further show that our approach provides a broader transferring range. The ablation study also show the regularization terms are critical for long range policy transfer. Finally, we show that our method consistently outperforms other methods when the quality of the primitives varies.

Indoor panorama typically consists of human-made structures parallel or perpendicular to gravity. We leverage this phenomenon to approximate the scene in a 360-degree image with (H)orizontal-planes and (V)ertical-planes. To this end, we propose an effective divide-and-conquer strategy that divides pixels based on their plane orientation estimation; then, the succeeding instance segmentation module conquers the task of planes clustering more easily in each plane orientation group. Besides, parameters of V-planes depend on camera yaw rotation, but translation-invariant CNNs are less aware of the yaw change. We thus propose a yaw-invariant V-planar reparameterization for CNNs to learn. We create a benchmark for indoor panorama planar reconstruction by extending existing 360 depth datasets with ground truth H&V-planes (referred to as "PanoH&V" dataset) and adopt state-of-the-art planar reconstruction methods to predict H&V-planes as our baselines. Our method outperforms the baselines by a large margin on the proposed dataset.

We present HoHoNet, a versatile and efficient framework for holistic understanding of an indoor 360-degree panorama using a Latent Horizontal Feature (LHFeat). The compact LHFeat flattens the features along the vertical direction and has shown success in modeling per-column modality for room layout reconstruction. HoHoNet advances in two important aspects. First, the deep architecture is redesigned to run faster with improved accuracy. Second, we propose a novel horizon-to-dense module, which relaxes the per-column output shape constraint, allowing per-pixel dense prediction from LHFeat. HoHoNet is fast: It runs at 52 FPS and 110 FPS with ResNet-50 and ResNet-34 backbones respectively, for modeling dense modalities from a high-resolution 512 × 1024 panorama. HoHoNet is also accurate. On the tasks of layout estimation and semantic segmentation, HoHoNet achieves results on par with current state-of-the-art. On dense depth estimation, HoHoNet outperforms all the prior arts by a large margin. Code is available at https://github.com/sunset1995/HoHoNet.

Although significant progress has been made in room layout estimation, most methods aim to reduce the loss in the 2D pixel coordinate rather than exploiting the room structure in the 3D space. Towards reconstructing the room layout in 3D, we formulate the task of 360° layout estimation as a problem of predicting depth on the horizon line of a panorama. Specifically, we propose the Differentiable Depth Rendering procedure to make the conversion from layout to depth prediction differentiable, thus making our proposed model end-to-end trainable while leveraging the 3D geometric information, without the need of providing the ground truth depth. Our method achieves state-of-the-art performance on numerous 360° layout benchmark datasets. Moreover, our formulation enables a pre-training step on the depth dataset, which further improves the generalizability of our layout estimation model.

We present a novel pyramidal output representation to ensure parsimony with our "specialize and fuse" process for semantic segmentation. A pyramidal "output" representation consists of coarse-to-fine levels, where each level is "specialize" in a different class distribution (e.g., more stuff than things classes at coarser levels). Two types of pyramidal outputs (i.e., unity and semantic pyramid) are "fused" into the final semantic output, where the unity pyramid indicates unity-cells (i.e., all pixels in such cell share the same semantic label). The process ensures parsimony by predicting a relatively small number of labels for unity-cells (e.g., a large cell of grass) to build the final semantic output. In addition to the "output" representation, we design a coarse-to-fine contextual module to aggregate the "features" representation from different levels. We validate the effectiveness of each key module in our method through comprehensive ablation studies. Finally, our approach achieves state-of-the-art performance on three widely-used semantic segmentation datasets—ADE20K, COCO-Stuff, and Pascal-Context.

In this paper, we present a novel preconditioning strategy for the classic 8-point algorithm (8-PA) for estimating an essential matrix from 360-FoV images (i.e., equirectangular images) in spherical projection. To alleviate the effect of uneven key-feature distributions and outlier correspondences, which can potentially decrease the accuracy of an essential matrix, our method optimizes a non-rigid transformation to deform a spherical camera into a new spatial domain, defining a new constraint and a more robust and accurate solution for an essential matrix. Through several experiments using random synthetic points, 360-FoV, and fish-eye images, we demonstrate that our normalization can increase the camera pose accuracy about 20% without significantly overhead the computation time. In addition, we present further benefits of our method through both a constant weighted least-square optimization that improves further the well known Gold Standard Method (GSM) (i.e., the non-linear optimization by using epipolar errors); and a relaxation of the number of RANSAC iterations, both showing that our normalization outcomes a more reliable, robust, and accurate solution.

We propose a canonical point autoencoder (CPAE) that predicts dense correspondences between 3D shapes of the same category. The autoencoder performs two key functions: (a) encoding an arbitrarily ordered point cloud to a canonical primitive, e.g., a sphere, and (b) decoding the primitive back to the original input instance shape. As being placed in the bottleneck, this primitive plays a key role to map all the unordered point clouds on the canonical surface, and to be reconstructed in an ordered fashion. Once trained, points from different shape instances that are mapped to the same locations on the primitive surface are determined to be a pair of correspondence. Our method does not require any form of annotation or self-supervised part segmentation network and can handle unaligned input point clouds within a certain rotation range. Experimental results on 3D semantic keypoint transfer and part segmentation transfer show that our model performs favorably against state-of-the-art correspondence learning methods.

Conventional Neural Architecture Search (NAS) aims at finding a single architecture that achieves the best performance, which usually optimizes task related learning objectives such as accuracy. However, a single architecture may not be representative enough for the whole dataset with high diversity and variety. Intuitively, electing domain-expert architectures that are proficient in domain-specific features can further benefit architecture related objectives such as latency. In this paper, we propose InstaNAS—an instance-aware NAS framework—that employs a controller trained to search for a “distribution of architectures” instead of a single architecture; This allows the model to use sophisticated architectures for the difficult samples, which usually comes with large architecture related cost, and shallow architectures for those easy samples. During the inference phase, the controller assigns each of the unseen input samples with a domain expert architecture that can achieve high accuracy with customized inference costs. Experiments within a search space inspired by MobileNetV2 show InstaNAS can achieve up to 48.8% latency reduction without compromising accuracy on a series of datasets against MobileNetV2.

Depth estimation from a monocular 360 image is an emerging problem that gains popularity due to the availability of consumer-level 360 cameras and the complete surrounding sensing capability. While the standard of 360 imaging is under rapid development, we propose to predict the depth map of a monocular 360 image by mimicking both peripheral and foveal vision of the human eye. To this end, we adopt a two-branch neural network leveraging two common projections: equirectangular and cubemap projections. In particular, equirectangular projection incorporates a complete field-of-view but introduces distortion, whereas cubemap projection avoids distortion but introduces discontinuity at the boundary of the cube. Thus we propose a bi-projection fusion scheme along with learnable masks to balance the feature map from the two projections. Moreover, for the cubemap projection, we propose a spherical padding procedure which mitigates discontinuity at the boundary of each face. We apply our method to four panorama datasets and show favorable results against the existing state-of-the-art methods.

Recently, end-to-end trainable deep neural networks have significantly improved stereo depth estimation for perspective images. However, 360° images captured under equirectangular projection cannot benefit from directly adopting existing methods due to distortion introduced (i.e., lines in 3D are not projected onto lines in 2D). To tackle this issue, we present a novel architecture specifically designed for spherical disparity using the setting of top-bottom 360° camera pairs. Moreover, we propose to mitigate the distortion issue by (1) an additional input branch capturing the position and relation of each pixel in the spherical coordinate, and (2) a cost volume built upon a learnable shifting filter. Due to the lack of 360° stereo data, we collect two 360° stereo datasets from Matterport3D and Stanford3D for training and evaluation. Extensive experiments and ablation study are provided to validate our method against existing algorithms. Finally, we show promising results on real-world environments capturing images with two consumer-level cameras. Our project page is at https://albert100121.github.io/360SD-Net-Project-Page.

Online continual learning is a challenging scenario where a model needs to learn from a continuous stream of data without revisiting any previously encountered data instances. The phenomenon of catastrophic forgetting is worsened since the model should not only address the forgetting at the task-level but also at the data instance-level within the same task. To mitigate this, we leverage the concept of "instance awareness" in the neural network, where each data instance is classified by a path in the network searched by the controller from a meta-graph. To preserve the knowledge we learn from previous instances, we proposed a method to protect the path by restricting the gradient updates of one instance from overriding past updates calculated from previous instances if these instances are not similar. On the other hand, it also encourages fine-tuning the path if the incoming instance shares the similarity with previous instances. The mechanism of selecting paths according to instances similarity is naturally determined by the controller, which is compact and online updated. Experimental results show that the proposed method outperforms state-of-the-arts in online continual learning. Furthermore, the proposed method is evaluated against a realistic setting where the boundaries between tasks are blurred. Experimental results confirm that the proposed method outperforms the state-of-the-arts on CIFAR-10, CIFAR-100, and Tiny-ImageNet.

In this work, we introduce VQA 360°, a novel task of visual question answering on 360° images. Unlike a normal field-of-view image, a 360° image captures the entire visual content around the optical center of a camera, demanding more sophisticated spatial understanding and reasoning. To address this problem, we collect the first VQA 360° dataset, containing around 17,000 real-world image-question-answer triplets for a variety of question types. We then study two different VQA models on VQA 360°, including one conventional model that takes an equirectangular image (with intrinsic distortion) as input and one dedicated model that first projects a 360° image onto cubemaps and subsequently aggregates the information from multiple spatial resolutions. We demonstrate that the cubemap-based model with multi-level fusion and attention diffusion performs favorably against other variants and the equirectangular-based models. Nevertheless, the gap between the humans' and machines' performance reveals the need for more advanced VQA 360° algorithms. We, therefore, expect our dataset and studies to serve as the benchmark for future development in this challenging task. Dataset, code, and pre-trained models are available online.

While there are several widely used object detection datasets, current computer vision algorithms are still limited in conventional images. Such images narrow our vision in a restricted region. On the other hand, 360° images provide a thorough sight. In this paper, our goal is to provide a standard dataset to facilitate the vision and machine learning communities in 360° domain. To facilitate the research, we present a real-world 360° panoramic object detection dataset, 360-Indoor, which is a new benchmark for visual object detection and class recognition in 360° indoor images. It is achieved by gathering images of complex indoor scenes containing common objects and the intensive annotated bounding field-of-view. In addition, 360-Indoor has several distinct properties: (1) the largest category number (37 labels in total). (2) the most complete annotations on average (27 bounding boxes per image). The selected 37 objects are all common in indoor scene. With around 3k images and 90k labels in total, 360-Indoor achieves the largest dataset for detection in 360° images. In the end, extensive experiments on the state-of-the-art methods for both classification and detection are provided. We will release this dataset in the near future.

Most of the existing works on image description focus on generating expressive descriptions. The only few works that are dedicated to generating stylish (e.g., romantic, lyric, etc.) descriptions suffer from limited style variation and content digression. To address these limitations, we propose a controllable stylish image description generation model. It can learn to generate stylish image descriptions that are more related to image content and can be trained with the arbitrary monolingual corpus without collecting new paired image and stylish descriptions. Moreover, it enables users to generate various stylish descriptions by plugging in style-specific parameters to include new styles into the existing model. We achieve this capability via a novel layer normalization layer design, which we will refer to as the Domain Layer Norm (DLN). Extensive experimental validation and user study on various stylish image description generation tasks are conducted to show the competitive advantages of the proposed model.

We present a new approach to the problem of estimating the 3D room layout from a single panoramic image. We represent room layout as three 1D vectors that encode, at each image column, the boundary positions of floor-wall and ceiling-wall, and the existence of wall-wall boundary. The proposed network, HorizonNet, trained for predicting 1D layout, outperforms previous state-of-the-art approaches. The designed post-processing procedure for recovering 3D room layouts from 1D predictions can automatically infer the room shape with low computation cost - it takes less than 20ms for a panorama image while prior works might need dozens of seconds. We also propose Pano Stretch Data Augmentation, which can diversify panorama data and be applied to other panorama-related learning tasks. Due to the limited data available for non-cuboid layout, we relabel 65 general layout from the current dataset for finetuning. Our approach shows good performance on general layouts by qualitative results and cross-validation.

We present a deep learning framework, called DuLa-Net, to predict Manhattan-world 3D room layouts from a single RGB panorama. To achieve better prediction accuracy, our method leverages two projections of the panorama at once, namely the equirectangular panorama-view and the perspective ceiling-view, that each contains different clues about the room layouts. Our network architecture consists of two encoder-decoder branches for analyzing each of the two views. In addition, a novel feature fusion structure is proposed to connect the two branches, which are then jointly trained to predict the 2D floor plans and layout heights. To learn more complex room layouts, we introduce the Realtor360 dataset that contains panoramas of Manhattan-world room layouts with different numbers of corners. Experimental results show that our work outperforms recent state-of-the-art in prediction accuracy and performance, especially in the rooms with non-cuboid layouts.

Vehicle 3D extents and trajectories are critical cues for predicting the future location of vehicles and planning future agent ego-motion based on those predictions. In this paper, we propose a novel online framework for 3D vehicle detection and tracking from monocular videos. The framework can not only associate detections of vehicles in motion over time, but also estimate their complete 3D bounding box information from a sequence of 2D images captured on a moving platform. Our method leverages 3D box depth-ordering matching for robust instance association and utilizes 3D trajectory prediction for re-identification of occluded vehicles. We also design a motion learning module based on an LSTM for more accurate long-term motion extrapolation. Our experiments on simulation, KITTI, and Argoverse datasets show that our 3D tracking pipeline offers robust data association and tracking. On Argoverse, our image-based method is significantly better for tracking 3D vehicles within 30 meters than the LiDAR-centric baseline methods.

While image synthesis achieves tremendous breakthroughs (e.g., generating realistic faces), video generation is less explored and harder to control, which limits its applications in the real world. For instance, video editing requires temporal coherence across multiple clips and thus poses both start and end constraints within a video sequence. We introduce point-to-point video generation that controls the generation process with two control points: the targeted start- and end-frames. The task is challenging since the model not only generates a smooth transition of frames but also plans ahead to ensure that the generated end-frame conforms to the targeted end-frame for videos of various lengths. We propose to maximize the modified variational lower bound of conditional data likelihood under a skip-frame training strategy. Our model can generate end-frame-consistent sequences without loss of quality and diversity. We evaluate our method through extensive experiments on Stochastic Moving MNIST, Weizmann Action, Human3.6M, and BAIR Robot Pushing under a series of scenarios. The qualitative results showcase the effectiveness and merits of point-to-point generation.

We propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input. Given any pre-trained depth prediction model, our PnP module updates the intermediate feature map such that the model outputs new depths consistent with the given sparse depths. Our method requires no additional training and can be applied to practical applications such as leveraging both RGB and sparse LiDAR points to robustly estimate dense depth map. Our approach achieves consistent improvements on various state-of-the-art methods on indoor (i.e., NYU-v2) and outdoor (i.e., KITTI) datasets. Various types of LiDARs are also synthesized in our experiments to verify the general applicability of our PnP module in practice.

The complementary characteristics of active and passive depth sensing techniques motivate the fusion of the LiDAR sensor and stereo camera for improved depth perception. Instead of directly fusing estimated depths across LiDAR and stereo modalities, we take advantages of the stereo matching network with two enhanced techniques: Input Fusion and Conditional Cost Volume Normalization (CCVNorm) on the LiDAR information. The proposed framework is generic and closely integrated with the cost volume component that is commonly utilized in stereo matching neural networks. We experimentally verify the efficacy and robustness of our method on the KITTI Stereo and Depth Completion datasets, obtaining favorable performance against various fusion strategies. Moreover, we demonstrate that, with a hierarchical extension of CCVNorm, the proposed method brings only slight overhead to the stereo matching network in terms of computation time and model size.

Narrated 360° videos are typically provided in many touring scenarios to mimic real-world experience. However, previous work has shown that smart assistance (i.e., providing visual guidance) can significantly help users to follow the Normal Field of View (NFoV) corresponding to the narrative.In this project, we aim at automatically grounding the NFoVs of a 360° video given subtitles of the narrative (referred to as ''NFoV-grounding"). We propose a novel Visual Grounding Model (VGM) to implicitly and efficiently predict the NFoVs given the video content and subtitles. Specifically, at each frame, we efficiently encode the panorama into feature map of candidate NFoVs using a Convolutional Neural Network (CNN) and the subtitles to the same hidden space using an RNN with Gated Recurrent Units (GRU). Then, we apply soft-attention on candidate NFoVs to trigger sentence decoder aiming to minimize the reconstruct loss between the generated and given sentence. Finally, we obtain the NFoV as the candidate NFoV with the maximum attention without any human supervision.To train VGM more robustly, we also generate a reverse sentence conditioning on one minus the soft-attention such that the attention focuses on candidate NFoVs less relevant to the given sentence. The negative log reconstruction loss of the reverse sentence (referred to as ''irrelevant loss") is jointly minimized to encourage the reverse sentence to be different from the given sentence. To evaluate our method, we collect the first narrated 360° videos dataset and achieve state-of-the-art NFoV-grounding performance.

Automatic saliency prediction in 360° videos is critical for viewpoint guidance applications (e.g., Facebook 360 Guide). We propose a spatial-temporal network which is (1) weakly-supervised trained and (2) tailor-made for 360° viewing sphere. Note that most existing methods are less scalable since they rely on annotated saliency map for training. Most importantly, they convert 360° sphere to 2D images (e.g., a single equirectangular image or multiple separate Normal Field-of-View (NFoV) images) which introduces distortion and image boundaries. In contrast, we propose a simple and effective Cube Padding (CP) technique as follows. Firstly, we render the 360° view on six faces of a cube using perspective projection. Thus, it introduces very little distortion. Then, we concatenate all six faces while utilizing the connectivity between faces on the cube for image padding (i.e., Cube Padding) in convolution, pooling, convolutional LSTM layers. In this way, CP introduces no image boundary while being applicable to almost all Convolutional Neural Network (CNN) structures. To evaluate our method, we propose Wild-360, a new 360° video saliency dataset, containing challenging videos with saliency heatmap annotations. In experiments, our method outperforms baseline methods in both speed and quality.

Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However, most existing works only optimize for model accuracy and largely ignore other important factors imposed by the underlying hardware and devices, such as latency and energy, when making inference. In this paper, we first introduce the problem of NAS and provide a survey on recent works. Then we deep dive into two recent advancements on extending NAS into multiple-objective frameworks: MONAS [19] and DPP-Net [10]. Both MONAS and DPP-Net are capable of optimizing accuracy and other objectives imposed by devices, searching for neural architectures that can be best deployed on a wide spectrum of devices: from embedded systems and mobile devices to workstations. Experimental results are poised to show that architectures found by MONAS and DPP-Net achieves Pareto optimality w.r.t the given objectives for various devices.

Visual place recognition is challenging, especially when only a few place exemplars are given. To mitigate the challenge, we consider place recognition method using omnidirectional cameras and propose a novel Omnidirectional Convolutional Neural Network (O-CNN) to handle severe camera pose variation. Given a visual input, the task of the O-CNN is not to retrieve the matched place exemplar, but to retrieve the closest place exemplar and estimate the relative distance between the input and the closest place. With the ability to estimate relative distance, a heuristic policy is proposed to navigate a robot to the retrieved closest place. Note that the network is designed to take advantage of the omnidirectional view by incorporating circular padding and rotation invariance. To train a powerful O-CNN, we build a virtual world for training on a large scale. We also propose a continuous lifted structured feature embedding loss to learn the concept of distance efficiently. Finally, our experimental results confirm that our method achieves state-of-the-art accuracy and speed with both the virtual world and real-world datasets.

We develop a Deep Learning-based Wearable Vision-system with Vibrotactile-feedback (DLWV2)to guide Blind and Visually Impaired (BVI)people to reach objects. The system achieves high accuracy in object detection and tracking in 3-D using an extended deep learning-based 2.5-D detector and a 3-D object tracker with the ability to track 3-D object locations even outside the camera field-of-view. We train our detector with a large number of images with 2.5-D object ground-truth (i.e., 2-D object bounding boxes and distance from the camera to objects). A novel combination of HTC Vive Tracker with our system enables us to automatically obtain the ground-truth labels for training while requiring very little human effort to set up the system. Moreover, our system processes frames in real-time through a client-server computing platform such that BVI people can receive realtime vibrotactile guidance. We conduct a thorough user study on 12 BVI people in new environments with object instances which are unseen during training. Our system outperforms the non-assistive guiding strategy with statistic significance in both time and the number of contacting irrelevant objects. Finally, the interview with BVI users confirms that our system with distance-based vibrotactile feedback is mostly preferred, especially for objects requiring gentle manipulation such as a bottle with water inside.

We propose a scalable approach to learn video-based question answering (QA): to answer a free-form natural language question about the contents of a video. Our approach automatically harvests a large number of videos and descriptions freely available online. Then, a large number of candidate QA pairs are automatically generated from descriptions rather than manually annotated. Next, we use these candidate QA pairs to train a number of video-based QA methods extended from MN (Sukhbaatar et al. 2015), VQA (Antol et al. 2015), SA (Yao et al. 2015), and SS (Venugopalan et al. 2015). In order to handle non-perfect candidate QA pairs, we propose a self-paced learning procedure to iteratively identify them and mitigate their effects in training. Finally, we evaluate performance on manually generated video-based QA pairs. The results show that our self-paced learning procedure is effective, and the extended SS model outperforms various baselines.

360° videos give viewers a spherical view and immersive experience of surroundings. However, one challenge of watching 360° videos is continuously focusing and re-focusing intended targets. To address this challenge, we developed two Focus Assistance techniques: Auto Pilot (directly bringing viewers to the target), and Visual Guidance (indicating the direction of the target). We conducted an experiment to measure viewers' video-watching experience and discomfort using these techniques and obtained their qualitative feedback. We showed that: 1) Focus Assistance improved ease of focus. 2) Focus Assistance techniques have specificity to video content. 3) Participants' preference of and experience with Focus Assistance depended not only on individual difference but also on their goal of watching the video. 4) Factors such as view-moving-distance, salience of the intended target and guidance, and language comprehension affected participants' video-watching experience. Based on these findings, we provide design implications for better 360° video focus assistance.

Watching a 360° sports video requires a viewer to continuously select a viewing angle, either through a sequence of mouse clicks or head movements. To relieve the viewer from this “360 piloting” task, we propose “deep 360 pilot” - a deep learning-based agent for piloting through 360° sports videos automatically. At each frame, the agent observes a panoramic image and has the knowledge of previously selected viewing angles. The task of the agent is to shift the current viewing angle (i.e. action) to the next preferred one (i.e., goal). We propose to directly learn an online policy of the agent from data. Specifically, we leverage a state-of-the-art object detector to propose a few candidate objects of interest (yellow boxes in Fig. 1). Then, a recurrent neural network is used to select the main object (green dash boxes in Fig. 1). Given the main object and previously selected viewing angles, our method regresses a shift in viewing angle to move to the next one. We use the policy gradient technique to jointly train our pipeline, by minimizing: (1) a regression loss measuring the distance between the selected and ground truth viewing angles, (2) a smoothness loss encouraging smooth transition in viewing angle, and (3) maximizing an expected reward offocusing on a foreground object. To evaluate our method, we built a new 360-Sports video dataset consisting offive sports domains. We trained domain-specific agents and achieved the best performance on viewing angle selection accuracy and users' preference compared to [53] and other baselines.

For survival, a living agent (e.g., human in Fig. 1(a)) must have the ability to assess risk (1) by temporally anticipating accidents before they occur (Fig. 1(b)), and (2) by spatially localizing risky regions (Fig. 1(c)) in the environment to move away from threats. In this paper, we take an agent-centric approach to study the accident anticipation and risky region localization tasks. We propose a novel soft-attention Recurrent Neural Network (RNN) which explicitly models both spatial and appearance-wise non-linear interaction between the agent triggering the event and another agent or static-region involved. In order to test our proposed method, we introduce the Epic Fail (EF) dataset consisting of 3000 viral videos capturing various accidents. In the experiments, we evaluate the risk assessment accuracy both in the temporal domain (accident anticipation) and spatial domain (risky region localization) on our EF dataset and the Street Accident (SA) dataset. Our method consistently outperforms other baselines on both datasets.

We introduce a general framework for visual forecasting, which directly imitates visual sequences without additional supervision. As a result, our model can be applied at several semantic levels and does not require any domain knowledge or handcrafted features. We achieve this by formulating visual forecasting as an inverse reinforcement learning (IRL) problem, and directly imitate the dynamics in natural sequences from their raw pixel values. The key challenge is the high-dimensional and continuous state-action space that prohibits the application of previous IRL algorithms. We address this computational bottleneck by extending recent progress in model-free imitation with trainable deep feature representations, which (1) bypasses the exhaustive state-action pair visits in dynamic programming by using a dual formulation and (2) avoids explicit state sampling at gradient computation using a deep feature reparametrization. This allows us to apply IRL at scale and directly imitate the dynamics in high-dimensional continuous visual sequences from the raw pixel values. We evaluate our approach at three different level-of-abstraction, from low level pixels to higher level semantics: future frame generation, action anticipation, visual story forecasting. At all levels, our approach outperforms existing methods.

We introduce two tactics, namely the strategically-timed attack and the enchanting attack, to attack reinforcement learning agents trained by deep reinforcement learning algorithms using adversarial examples. In the strategically-timed attack, the adversary aims at minimizing the agent's reward by only attacking the agent at a small subset of time steps in an episode. Limiting the attack activity to this subset helps prevent detection of the attack by the agent. We propose a novel method to determine when an adversarial example should be crafted and applied. In the enchanting attack, the adversary aims at luring the agent to a designated target state. This is achieved by combining a generative model and a planning algorithm: while the generative model predicts the future states, the planning algorithm generates a preferred sequence of actions for luring the agent. A sequence of adversarial examples is then crafted to lure the agent to take the preferred sequence of actions. We apply the proposed tactics to the agents trained by the state-of-the-art deep reinforcement learning algorithm including DQN and A3C. In 5 Atari games, our strategically-timed attack reduces as much reward as the uniform attack (i.e., attacking at every time step) does by attacking the agent 4 times less often. Our enchanting attack lures the agent toward designated target states with a more than 70% success rate. Example videos are available at http://yclin.me/adversarial_attack_RL/.

Photo composition is an important factor affecting the aesthetics in photography. However, it is a highly challenging task to model the aesthetic properties of good compositions due to the lack of globally applicable rules to the wide variety of photographic styles. Inspired by the thinking process of photo taking, we formulate the photo composition problem as a view finding process which successively examines pairs of views and determines their aesthetic preferences. We further exploit the rich professional photographs on the web to mine unlimited high-quality ranking samples and demonstrate that an aesthetics-aware deep ranking network can be trained without explicitly modeling any photographic rules. The resulting model is simple and effective in terms of its architectural design and data sampling method. It is also generic since it naturally learns any photographic rules implicitly encoded in professional photographs. The experiments show that the proposed view finding network achieves state-of-the-art performance with sliding window search strategy on two image cropping datasets.

We present a novel method to summarize unconstrained videos using salient montages (i.e., a "melange" of frames in the video as shown in Fig. 1, by finding "montageable moments" and identifying the salient people and actions to depict in each montage. Our method aims at addressing the increasing need for generating concise visualizations from the large number of videos being captured from portable devices. Our main contributions are (1) the process of finding salient people and moments to form a montage, and (2) the application of this method to videos taken "in the wild" where the camera moves freely. As such, we demonstrate results on head-mounted cameras, where the camera moves constantly, as well as on videos downloaded from YouTube. In our experiments, we show that our method can reliably detect and track humans under significant action and camera motion. Moreover, the predicted salient people are more accurate than results from state-of-the-art video salieny method [1] . Finally, we demonstrate that a novel "montageability" score can be used to retrieve results with relatively high precision which allows us to present high quality montages to users.We present a novel method to summarize unconstrained videos using salient montages (i.e., a "melange" of frames in the video as shown in Fig. 1, by finding "montageable moments" and identifying the salient people and actions to depict in each montage. Our method aims at addressing the increasing need for generating concise visualizations from the large number of videos being captured from portable devices. Our main contributions are (1) the process of finding salient people and moments to form a montage, and (2) the application of this method to videos taken "in the wild" where the camera moves freely. As such, we demonstrate results on head-mounted cameras, where the camera moves constantly, as well as on videos downloaded from YouTube. In our experiments, we show that our method can reliably detect and track humans under significant action and camera motion. Moreover, the predicted salient people are more accurate than results from state-of-the-art video salieny method [1] . Finally, we demonstrate that a novel "montageability" score can be used to retrieve results with relatively high precision which allows us to present high quality montages to users.

Due to the unprecedented growth of unedited videos, finding highlights relevant to a text query in a set of unedited videos has become increasingly important. We refer this task as semantic highlight retrieval and propose a query-dependent video representation for retrieving a variety of highlights. Our method consists of two parts: 1) "viralets", a mid-level representation bridging between semantic [Fig. 1(a)] and visual [Fig. 1(c)] spaces and 2) a novel Semantic-MODulation (SMOD) procedure to make viralets query-dependent (referred to as SMOD viralets). Given SMOD viralets, we train a single highlight ranker to predict the highlightness of clips with respect to a variety of queries (two examples in Fig. 1), whereas existing approaches can be applied only in a few predefined domains. Other than semantic highlight retrieval, viralets can also be used to associate relevant terms to each video. We utilize this property and propose a simple term prediction method based on nearest neighbor search. To conduct experiments, we collect a viral video dataset including users' comments, highlights, and/or original videos. Among a testing database with 1189 clips (13% highlights and 87% non-highlights), our highlight ranker achieves 41.2% recall at top-10 retrieved clips. It is significantly higher than the state-of-the-art domain-specific highlight ranker and its extension. Similarly, our method also outperforms all baseline methods on the publicly available video highlight dataset. Finally, our simple term prediction method utilizing viralets outperforms the state-of-the-art matrix factorization method (adapted from Kalayeh et al.). Viral videos refer to popular online videos. We focus on user-generated viral videos, which typically contain short highlight marked by users.

We propose a novel sensing technique called proactive sensing. Proactive sensing continually repositions a camera-based sensor as a way to improve hand pose estimation. Our core contribution is a scheme that effectively learns how to move the sensor to improve pose estimation confidence while requiring no ground truth hand poses. We demonstrate this concept using a low-cost rapid swing arm system built around the state-of-the-art commercial sensing system Leap Motion. The results from our user study show that proactive sensing helps estimate users' hand poses with higher confidence compared to both static and random sensing. We further present an online model update to improve performance for each user.

Finding highlights relevant to a text query in unedited videos has become increasingly important due to their unprecedented growth. We refer this task as semantic highlight retrieval and propose a query-dependent video representation for retrieving a variety of highlights. Our method consist of two parts: (1) “viralets”, a mid-level representation bridging between visual and semantic spaces; (2) a novel Semantically-Modulation (SM) procedure to make viralets query-dependent (referred to as SM viralets). Given SM viralets, we train a single highlight ranker to predict the highlightness of clips with respect to a variety of queries, whereas existing approaches can be applied only in a few predefined domains. We collect a viral video dataset1including users' comments, highlights, and/or original videos. Among a database with 1189 (13% highlights) clips, our highlight ranker achieves 41.2% recall at top-10 retrieved clips. It is significantly higher than a state-of-the-art domain-specific highlight ranker and its extension. Similarly, our method also outperforms all baseline methods on the video highlight dataset.

We present a fully automatic system for ranking domain-specific highlights in unconstrained personal videos by analyzing online edited videos. A novel latent linear ranking model is proposed to handle noisy training data harvested online. Specifically, given a targeted domain such as "surfing," our system mines the YouTube database to find pairs of raw and their corresponding edited videos. Leveraging the assumption that an edited video is more likely to contain highlights than the trimmed parts of the raw video, we obtain pair-wise ranking constraints to train our model. The learning task is challenging due to the amount of noise and variation in the mined data. Hence, a latent loss function is incorporated to mitigate the issues caused by the noise. We efficiently learn the latent model on a large number of videos (about 870 min in total) using a novel EM-like procedure. Our latent ranking model outperforms its classification counterpart and is fairly competitive compared with a fully supervised ranking system that requires labels from Amazon Mechanical Turk. We further show that a state-of-the-art audio feature mel-frequency cepstral coefficients is inferior to a state-of-the-art visual feature. By combining both audio-visual features, we obtain the best performance in dog activity, surfing, skating, and viral video domains. Finally, we show that impressive highlights can be detected without additional human supervision for seven domains (i.e., skating, surfing, skiing, gymnastics, parkour, dog activity, and viral video) in unconstrained personal videos.

In the last few years, substantially different approaches have been adopted for segmenting and detecting "things" (object categories that have a well defined shape such as people and cars) and "stuff" (object categories which have an amorphous spatial extent such as grass and sky). While things have been typically detected by sliding window or Hough transform based methods, detection of stuff is generally formulated as a pixel or segment-wise classification problem. This paper proposes a framework for scene understanding that models both things and stuff using a common representation while preserving their distinct nature by using a property list. This representation allows us to enforce sophisticated geometric and semantic relationships between thing and stuff categories via property interactions in a single graphical model. We use the latest advances made in the field of discrete optimization to efficiently perform maximum a posteriori (MAP) inference in this model. We evaluate our method on the Stanford dataset by comparing it against state-of-the-art methods for object segmentation and detection. We also show that our method achieves competitive performances on the challenging PASCAL '09 segmentation dataset.

Many methods have been proposed to solve the image classification problem for a large number of categories. Among them, methods based on tree-based representations achieve good trade-off between accuracy and test time efficiency. While focusing on learning a tree-shaped hierarchy and the corresponding set of classifiers, most of them [11, 2, 14] use a greedy prediction algorithm for test time efficiency. We argue that the dramatic decrease in accuracy at high efficiency is caused by the specific design choice of the learning and greedy prediction algorithms. In this work, we propose a classifier which achieves a better trade-off between efficiency and accuracy with a given tree-shaped hierarchy. First, we convert the classification problem as finding the best path in the hierarchy, and a novel branch-and-bound-like algorithm is introduced to efficiently search for the best path. Second, we jointly train the classifiers using a novel Structured SVM (SSVM) formulation with additional bound constraints. As a result, our method achieves a significant 4.65%, 5.43%, and 4.07% (relative 24.82%, 41.64%, and 109.79%) improvement in accuracy at high efficiency compared to state-of-the-art greedy "tree-based" methods [14] on Caltech-256 [15], SUN [32] and Image Net 1K [9] dataset, respectively. Finally, we show that our branch-and-bound-like algorithm naturally ranks the paths in the hierarchy (Fig. 8) so that users can further process them.

Mobile platforms such as smart-phones and tablet computers have attained the technological capacity to perform tasks beyond their intended purposes. The steady increase of processing power has enticed researchers to attempt increasingly challenging tasks on mobile devices with appropriate modifications over their stationary counterparts. In this work we present a novel multi-frame object detection application for the mobile platform that is capable of object localization. Our work leverages the hough forest based object detector introduced by Gall et al. in [10]. In our experiments, we demonstrate that our novel, multi-frame generalization of [10] notably improves the detection performance. We test the performance of the technique in variable resolutions, the applicability to several object categories and different datasets. We implement the multi-frame detector on a mobile platform through a novel client-server framework that presents a sound and viable environment for the multi-frame detector. Finally, we study implementations of both single and multi-frame object detectors based on this client-server framework on a mobile device running the android OS.

Random forests have been successfully applied to various high level computer vision tasks such as human pose estimation and object segmentation. These models are extremely efficient but work under the assumption that the output variables (such as body part locations or pixel labels) are independent. In this paper, we present a conditional regression forest model for human pose estimation that incorporates dependency relationships between output variables through a global latent variable while still maintaining a low computational cost. We show that the incorporation of a global latent variable encoding torso orientation, or human height, etc., can dramatically increase the accuracy of body joint location prediction. Our model also allows efficient and seamless incorporation of prior knowledge about the problem instance such as the height or orientation of the human subject which can be available from the problem context or via a temporal model. We show that our method significantly outperforms state-of-the-art methods for pose estimation from depth images. The conditional regression model proposed in the paper is general and can be applied to other problems where random forests are used.

Human pose estimation in a static image is a challenging problem in computer vision in that body part configurations are often subject to severe deformations and occlusions. Moreover, efficient pose estimation is often a desirable requirement in many applications. The trade-off between accuracy and efficiency has been explored in a large number of approaches. On the one hand, models with simple representations (like tree or star models) can be efficiently applied in pose estimation problems. However, these models are often prone to body part misclassification errors. On the other hand, models with rich representations (i.e., loopy graphical models) are theoretically more robust, but their inference complexity may increase dramatically. In this work, we propose an efficient and exact inference algorithm based on branch-and-bound to solve the human pose estimation problem on loopy graphical models. We show that our method is empirically much faster (about 74 times) than the state-of-the-art exact inference algorithm [21]. By extending a state-of-the-art tree model [16] to a loopy graphical model, we show that the estimation accuracy improves for most of the body parts (especially lower arms) on popular datasets such as Buffy [7] and Stickmen [5] datasets. Finally, our method can be used to exactly solve most of the inference problems on Stretchable Models [18] (which contains a few hundreds of variables) in just a few minutes.

Despite recent successes, pose estimators are still somewhat fragile, and they frequently rely on a precise knowledge of the location of the object. Unfortunately, articulated objects are also very difficult to detect. Knowledge about the articulated nature of these objects, however, can substantially contribute to the task of finding them in an image. It is somewhat surprising, that these two tasks are usually treated entirely separately. In this paper, we propose an Articulated Part-based Model (APM) for jointly detecting objects and estimating their poses. APM recursively represents an object as a collection of parts at multiple levels of detail, from coarse-to-fine, where parts at every level are connected to a coarser level through a parent-child relationship (Fig. 1(b)-Horizontal). Parts are further grouped into part-types (e.g., left-facing head, long stretching arm, etc) so as to model appearance variations (Fig. 1(b)-Vertical). By having the ability to share appearance models of part types and by decomposing complex poses into parent-child pairwise relationships, APM strikes a good balance between model complexity and model richness. Extensive quantitative and qualitative experiment results on public datasets show that APM outperforms state-of-the-art methods. We also show results on PASCAL 2007 - cats and dogs - two highly challenging articulated object categories.

Detecting objects in complex scenes while recovering the scene layout is a critical functionality in many vision-based applications. Inspired by the work of, we advocate the importance of geometric contextual reasoning for object recognition. We start from the intuition that objects' location and pose in the 3D space are not arbitrarily distributed but rather constrained by the fact that objects must lie on one or multiple supporting surfaces. We model such supporting surfaces by means of hidden parameters (i.e. not explicitly observed) and formulate the problem of joint scene reconstruction and object recognition as the one of finding the set of parameters that maximizes the joint probability of having a number of detected objects on K supporting planes given the observations. As a key ingredient for solving this optimization problem, we have demonstrated a novel relationship between object location and pose in the image, and the scene layout parameters (i.e. normal of one or more supporting planes in 3D and camera pose, location and focal length). Using the probabilistic formulation and the above relationship our method has the unique ability to jointly: (i) reduce false alarm and false negative object detection rate; (ii) recover object location and supporting planes within the 3D camera reference system; (iii) infer camera parameters (view point and the focal length) from just one single uncalibrated image. Quantitative and qualitative experimental evaluation on a number of datasets (a novel in-house dataset and label-me on car and pedestrian) demonstrates our theoretical claims.

We address the problem of recognizing the pose of an object category from video sequences capturing the object under small camera movements. This scenario is relevant in applications such as robotic object manipulation or autonomous navigation. We introduce a new algorithm where we model an object category as a collection of non parametric probability densities capturing appearance and geometrical variability within a small area of the viewing sphere for different object instances. By regarding the set of frames of the video as realizations of such probability densities, we cast the problem of object pose classification as the one of matching (i.e., comparing information divergence of) probably density functions in testing and training. Our work can be also related to statistical manifold learning. By performing dimensionality reduction on the manifold of learned PDFs, we show that the embedding in the 3D Euclidean space yield meaningful trajectories which can be parameterized by the pose coordinates on the viewing sphere, this enables an unsupervised learning procedure for pose classification. Our experimental results on both synthesized and real world data show promising results toward the goal of accurate and efficient pose classification of object categories from video sequences.

We propose a novel probabilistic framework for learning visual models of 3D object categories by combining appearance information and geometric constraints. Objects are represented as a coherent ensemble of parts that are consistent under 3D viewpoint transformations. Each part is a collection of salient image features. A generative framework is used for learning a model that captures the relative position of parts within each of the discretized viewpoints. Contrary to most of the existing mixture of viewpoints models, our model establishes explicit correspondences of parts across different viewpoints of the object class. Given a new image, detection and classification are achieved by determining the position and viewpoint of the model that maximize recognition scores of the candidate objects. Our approach is among the first to propose a generative probabilistic framework for 3D object categorization. We test our algorithm on the detection task and the viewpoint classification task by using “car” category from both the Savarese et al. 2007 and PASCAL VOC 2006 datasets. We show promising results in both the detection and viewpoint classification tasks on these two challenging datasets.

Recognizing object classes and their 3D viewpoints is an important problem in computer vision. Based on a part-based probabilistic representation [31], we propose a new 3D object class model that is capable of recognizing unseen views by pose estimation and synthesis. We achieve this by using a dense, multiview representation of the viewing sphere parameterized by a triangular mesh of viewpoints. Each triangle of viewpoints can be morphed to synthesize new viewpoints. By incorporating 3D geometrical constraints, our model establishes explicit correspondences among object parts across viewpoints. We propose an incremental learning algorithm to train the generative model. A cellphone video clip of an object is first used to initialize model learning. Then the model is updated by a set of unsorted training images without viewpoint labels. We demonstrate the robustness of our model on object detection, viewpoint classification and synthesis tasks. Our model performs superiorly to and on par with state-of-the-art algorithms on the Savarese et al. 2007 and PASCAL datasets in object detection. It outperforms all previous work in viewpoint classification and offers promising results in viewpoint synthesis.