3D skeletal action recognition has emerged as a powerful alternative to traditional RGB and depth-based approaches, offering robustness to environmental variations, computational efficiency, and enhanced privacy. Despite remarkable progress, current research remains fragmented across diverse input representations and lacks evaluation under scenarios that reflect real-world challenges. This paper presents a representation-centric review of supervised skeletal action recognition, systematically categorizing state-of-the-art methods by their input feature types: joint coordinates, bone vectors, motion flows, and extended representations, and analyzing how these choices influence spatiotemporal modeling strategies. Building on the insights from this review, we introduce ANUBIS, a large-scale, challenging dataset designed to address critical gaps in existing benchmarks. ANUBIS incorporates multi-view recordings with back-view perspectives, complex multi-person interactions, fine-grained and violent actions, and contemporary social behaviors. We benchmark a diverse set of state-of-the-art models on ANUBIS and conduct an in-depth analysis of how different feature types affect recognition performance across 102 action categories. Our results show strong action-feature dependencies, highlight the limitations of naïve multi-representational fusion, and point toward the need for task-aware, semantically aligned integration strategies. This work offers both a comprehensive foundation and a practical benchmarking resource, aiming to guide the next generation of robust, generalizable skeleton-based action recognition systems for complex real-world scenarios. The dataset, benchmarking framework, and code are available at https://yliu1082.github.io/ANUBIS/ .

While recent advancements have demonstrated remarkable progress in general 3D shape generation, the challenge of automatically generating wearable 3D assets remains largely unexplored. To address this gap, we present BAG - a Body-aligned Asset Generation method that produces 3D wearable assets which can be automatically fitted onto given 3D human bodies. This is achieved by controlling the 3D generation process using human body shape and pose information. Specifically, we first construct a general single-image-to-consistent-multi-view diffusion model, and train it on the large-scale Objaverse dataset to ensure diversity and generalizability. We then train a body-conditioned multi-view ControlNet to guide the generator toward producing body-aligned multi-view images. The control signal leverages multi-view 2D projections of the target human body, where pixel values represent the XYZ coordinates of the body surface in a canonical space. The resulting body-conditioned multi-view diffusion outputs body-aligned images, which are subsequently fed into a native 3D diffusion model to reconstruct the 3D shape of the asset. Finally, we recover the similarity transformation using multi-view silhouette supervision and mitigate asset-body penetration using physics-based simulation, ensuring accurate asset fitting onto the target body. Experimental results demonstrate that our method significantly outperforms existing approaches in terms of prompt adherence, shape diversity, and shape quality.

Most existing graph neural networks (GNNs) learn node embeddings using the framework of message passing and aggregation. Such GNNs are incapable of learning relative positions between graph nodes within a graph. To empower GNNs with the awareness of node positions, some nodes are set as anchors. Then, using the distances from a node to the anchors, GNNs can infer relative positions between nodes. However, position-aware GNNs (P-GNNs) arbitrarily select anchors, leading to compromising position awareness and feature extraction. To eliminate this compromise, we demonstrate that selecting evenly distributed and asymmetric anchors is essential. On the other hand, we show that choosing anchors that can aggregate embeddings of all the nodes within a graph is NP-complete. Therefore, devising efficient optimal algorithms in a deterministic approach is practically not feasible. To ensure position awareness and bypass NP-completeness, we propose position-sensing GNNs (PSGNNs), learning how to choose anchors in a backpropagatable fashion. Experiments verify the effectiveness of PSGNNs against state-of-the-art GNNs, substantially improving performance on various synthetic and real-world graph datasets while enjoying stable scalability. Specifically, PSGNNs on average boost area under the curve (AUC) more than 14% for pairwise node classification and 18% for link prediction over the existing state-of-the-art position-aware methods. Our source code is publicly available at: https://github.com/ZhenyueQin/PSGNN.

Given a single image of a 3D object, this paper proposes a novel method (named ConsistNet) that can generate multiple images of the same object, as if they are capturedfrom different viewpoints, while the 3D (multi-view) consistencies among those multiple generated images are effectively exploited. Central to our method is a lightweight multi-view consistency block that enables information exchange across multiple single-view diffusion processes based on the underlying multi-view geometry principles. ConsistNet is an extension to the standard latent diffusion model and it consists of two submodules: (a) a view aggregation module that unprojects multi-view features into global 3D volumes and infers consistency, and (b) a ray aggregation module that samples and aggregates 3D consistent features back to each view to enforce consistency. Our approach departs from previous methods in multi-view image generation, in that it can be easily dropped in pretrained LDMs without requiring explicit pixel correspondences or depth prediction. Experiments show that our method effectively learns 3D consistency over a frozen Zero123-XL backbone and can generate 16 surrounding views of the object within 11 seconds on a single A100 GPU. Our code will be made available on https://github.com/JiayuYANG/ConsistNet.

While showing promising results, recent RGB-D camera-based category-level object pose estimation methods have restricted applications due to the heavy reliance on depth sensors. RGB-only methods provide an alternative to this problem yet suffer from inherent scale ambiguity stemming from monocular observations. In this paper, we propose a novel pipeline that decouples the 6D pose and size estimation to mitigate the influence of imperfect scales on rigid transformations. Specifically, we leverage a pre-trained monocular estimator to extract local geometric information, mainly facilitating the search for inlier 2D-3D correspondence. Meanwhile, a separate branch is designed to directly recover the metric scale of the object based on category-level statistics. Finally, we advocate using the RANSAC-PnP algorithm to robustly solve for 6D object pose. Extensive experiments have been conducted on both synthetic and real datasets, demonstrating the superior performance of our method over previous state-of-the-art RGB-based approaches, especially in terms of rotation accuracy. Code: https://github.com/goldoak/DMSR.

Ensuring robust tracking of controllers’ movement is critical for human-robot interaction in virtual reality (VR) scenarios. This paper proposes a robust tracking algorithm based on a novel wearable ring-shaped controller equipped with an inertial measurement unit (IMU) and a light-emitting diode (LED). This novel controller design allows users to free up their hands for more immersive experiences. To track the controller’s motion accurately and robustly, we resort to various forms of visual measurements, including 6 DoF and 5 DoF pose measurements from hand gesture detection, as well as 3 DoF position measurement and 2 DoF image measurement derived from the LED. We theoretically analyze the performances of these observation models and propose an optimal observation model combination scheme. Moreover, the necessity and rationale of online estimating system gravity are illustrated. The effectiveness of our tracking method is validated through extensive experiments.

Large Reconstruction Models have made significant strides in the realm of automated 3D content generation from single or multiple input images. Despite their success, these models often produce 3D meshes with geometric inaccuracies, stemming from the inherent challenges of deducing 3D shapes solely from image data. In this work, we introduce a novel framework, the Large Image and Point Cloud Alignment Model (LAM3D), which utilizes 3D point cloud data to enhance the fidelity of generated 3D meshes. Our methodology begins with the development of a point-cloud-based network that effectively generates precise and meaningful latent tri-planes, laying the groundwork for accurate 3D mesh reconstruction. Building upon this, our Image-Point-Cloud Feature Alignment technique processes a single input image, aligning to the latent tri-planes to imbue image features with robust 3D information. This process not only enriches the image features but also facilitates the production of high-fidelity 3D meshes without the need for multi-view input, significantly reducing geometric distortions. Our approach achieves state-of-the-art high-fidelity 3D mesh reconstruction from a single image in just 6 seconds, and experiments on various datasets demonstrate its effectiveness.

Since language models (LMs) now outperform average humans on many challenging tasks, it is becoming increasingly difficult to develop challenging, high-quality, and realistic evaluations. We address this by examining LM capabilities to generate code for solving real scientific research problems. Incorporating input from scientists and AI researchers in 16 diverse natural science sub-fields, including mathematics, physics, chemistry, biology, and materials science, we create a scientist-curated coding benchmark, SciCode. The problems naturally factorize into multiple subproblems, each involving knowledge recall, reasoning, and code synthesis. In total, SciCode contains 338 subproblems decomposed from 80 challenging main problems, and it offers optional descriptions specifying useful scientific background information and scientist-annotated gold-standard solutions and test cases for evaluation. OpenAI o1-preview, the best-performing model among those tested, can solve only 7.7\% of the problems in the most realistic setting. We believe that SciCode demonstrates both contemporary LMs' progress towards realizing helpful scientific assistants and sheds light on the building and evaluation of scientific AI in the future.

We present Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass. Unlike existing methods that output a single, unified 3D shape, Frankenstein simultaneously generates multiple separated shapes, each corresponding to a semantically meaningful part. The 3D scene information is encoded in one single triplane tensor, from which multiple Signed Distance Function (SDF) fields can be decoded to represent the compositional shapes. During training, an auto-encoder compresses tri-planes into a latent space, and then the denoising diffusion process is employed to approximate the distribution of the compositional scenes. Frankenstein demonstrates promising results in generating room interiors as well as human avatars with automatically separated parts. The generated scenes facilitate many downstream applications, such as part-wise re-texturing, object rearrangement in the room or avatar cloth re-targeting.

Deep CNNs have achieved impressive improvements for night-time self-supervised depth estimation form a monocular image. However, the performance degrades considerably compared to day-time depth estimation due to significant domain gaps, low visibility, and varying illuminations between day and night images. To address these challenges, we propose a novel night-time self-supervised monocular depth estimation framework with structure regularization, i.e., SRNSD, which incorporates three aspects of constraints for better performance, including feature and depth domain adaptation, image perspective constraint, and cropped multi-scale consistency loss. Specifically, we utilize adaptations of both feature and depth output spaces for better night-time feature extraction and depth map prediction, along with high- and low-frequency decoupling operations for better depth structure and texture recovery. Meanwhile, we employ an image perspective constraint to enhance the smoothness and obtain better depth maps in areas where the luminosity jumps change. Furthermore, we introduce a simple yet effective cropped multi-scale consistency loss that utilizes consistency among different scales of depth outputs for further optimization, refining the detailed textures and structures of predicted depth. Experimental results on different benchmarks with depth ranges of 40m and 60m, including Oxford RobotCar dataset, nuScenes dataset and CARLA-EPE dataset, demonstrate the superiority of our approach over state-of-the-art night-time self-supervised depth estimation approaches across multiple metrics, proving our effectiveness.

Skeleton sequences are lightweight and compact and thus are ideal candidates for action recognition on edge devices. Recent skeleton-based action recognition methods extract features from 3-D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance. The use of first- and second-order features, that is, joint and bone representations, has led to high accuracy. Nonetheless, many models are still confused by actions that have similar motion trajectories. To address these issues, we propose fusing higher-order features in the form of angular encoding (AGE) into modern architectures to robustly capture the relationships between joints and body parts. This simple fusion with popular spatial-temporal graph neural networks achieves new state-of-the-art accuracy in two large benchmarks, including NTU60 and NTU120, while employing fewer parameters and reduced run time. Our source code is publicly available at: https://github.com/ZhenyueQin/Angular-Skeleton-Encoding.

We present BlockFusion, a diffusion-based model that generates 3D scenes as unit blocks and seamlessly incorporates new blocks to extend the scene. BlockFusion is trained using datasets of 3D blocks that are randomly cropped from complete 3D scene meshes. Through per-block fitting, all training blocks are converted into the hybrid neural fields: with a tri-plane containing the geometry features, followed by a Multi-layer Perceptron (MLP) for decoding the signed distance values. A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed. Diffusion applied to the latent representations allows for high-quality and diverse 3D scene generation. To expand a scene during generation, one needs only to append empty blocks to overlap with the current scene and extrapolate existing latent tri-planes to populate new blocks. The extrapolation is done by conditioning the generation process with the feature samples from the overlapping tri-planes during the denoising iterations. Latent tri-plane extrapolation produces semantically and geometrically meaningful transitions that harmoniously blend with the existing scene. A 2D layout conditioning mechanism is used to control the placement and arrangement of scene elements. Experimental results indicate that BlockFusion is capable of generating diverse, geometrically consistent and unbounded large 3D scenes with unprecedented high-quality shapes in both indoor and outdoor scenarios.

This paper presents a learning-based method for multi-view depth estimation from posed images. Our core idea is a “learning-to-optimize” paradigm that iteratively indexes a plane-sweeping cost volume and regresses the depth map via a convolutional Gated Recurrent Unit (GRU). Since the cost volume plays a paramount role in encoding the multi-view geometry, we aim to improve its construction both at pixel- and frame- levels. At the pixel level, we propose to break the symmetry of the Siamese network (which is typically used in MVS to extract image features) by introducing a transformer block to the reference image (but not to the source images). Such an asymmetric volume allows the network to extract global features from the reference image to predict its depth map. Given potential inaccuracies in the poses between reference and source images, we propose to incorporate a residual pose network to correct the relative poses. This essentially rectifies the cost volume at the frame level. We conduct extensive experiments on real-world MVS datasets and show that our method achieves state-of-the-art performance in terms of both within-dataset evaluation and cross-dataset generalization.

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for an improvement w.r.t model’s generalizability, performance, and training/inference memory footprint. The aforementioned benefits become ever so indispensable in the case of training for vision-related dense prediction tasks. In this work, we tackle the MTL problem of two dense tasks, i.e., semantic segmentation and depth estimation, and present a novel attention module called Cross-Channel Attention Module (CCAM), which facilitates effective feature sharing along each channel between the two tasks, leading to mutual performance gain with a negligible increase in trainable parameters. In a symbiotic spirit, we also formulate novel data augmentations for the semantic segmentation task using predicted depth called AffineMix, and one using predicted semantics called ColorAug, for depth estimation task. Finally, we validate the performance gain of the proposed method on the Cityscapes and ScanNet dataset. which helps us achieve state-of-the-art results for a semi-supervised joint model based on depth estimation and semantic segmentation.

Self-supervised monocular depth estimation has seen significant progress in recent years, especially in outdoor environments, i.e., autonomous driving scenes. However, depth prediction results are not satisfying in indoor scenes where most of the existing data are captured with hand-held devices. As compared to outdoor environments, estimating depth of monocular videos for indoor environments, using self-supervised methods, results in two additional challenges: (i) the depth range of indoor video sequences varies a lot across different frames, making it difficult for the depth network to induce consistent depth cues for training, whereas the maximum distance in outdoor scenes mostly stays the same as the camera usually sees the sky; (ii) the indoor sequences recorded with handheld devices often contain much more rotational motions, which cause difficulties for the pose network to predict accurate relative camera poses, while the motions of outdoor sequences are pre-dominantly translational, especially for street-scene driving datasets such as KITTI. In this work, we propose a novel framework-MonoIndoor++ by giving special considerations to those challenges and consolidating a set of good practices for improving the performance of self-supervised monocular depth estimation for indoor environments. First, a depth factorization module with transformer-based scale regression network is proposed to estimate a global depth scale factor explicitly, and the predicted scale factor can indicate the maximum depth values. Second, rather than using a single-stage pose estimation strategy as in previous methods, we propose to utilize a residual pose estimation module to estimate relative camera poses across consecutive frames iteratively. Third, to incorporate extensive coordinates guidance for our residual pose estimation module, we propose to perform coordinate convolutional encoding directly over the inputs to pose networks. The proposed method is validated on a variety of benchmark indoor datasets, i.e., EuRoC MAV, NYUv2, ScanNet and 7-Scenes, demonstrating the state-of-the-art performance. In addition, the effectiveness of each module is shown through a carefully conducted ablation study and the good generalization and universality of our trained model is also demonstrated, specifically on ScanNet and 7-Scenes datasets.

We present a novel framework named PlaneMVS for 3D plane reconstruction from multiple input views with known camera poses. Most previous learning-based plane reconstruction methods reconstruct 3D planes from single images, which highly rely on single-view regression and suffer from depth scale ambiguity. In contrast, we reconstruct 3D planes with a multi-view-stereo (MVS) pipeline that takes advantage of multi-view geometry. We decouple plane reconstruction into a semantic plane detection branch and a plane MVS branch. The semantic plane detection branch is based on a single-view plane detection framework but with differences. The plane MVS branch adopts a set of slanted plane hypotheses to replace conventional depth hypotheses to perform plane sweeping strategy and finally learns pixel-level plane parameters and its planar depth map. We present how the two branches are learned in a balanced way, and propose a soft-pooling loss to associate the outputs of the two branches and make them benefit from each other. Extensive experiments on various indoor datasets show that PlaneMVS significantly outperforms state-of-the-art (SOTA) single-view plane reconstruction methods on both plane detection and 3D geometry metrics. Our method even outperforms a set of SOTA learning-based MVS methods thanks to the learned plane priors. To the best of our knowledge, this is the first work on 3D plane reconstruction within an end-to-end MVS framework.

Video instance segmentation (VIS) task requires classifying, segmenting, and tracking object instances over all frames in a video clip. Recently, VisTR [1] has been proposed as end-to-end transformer-based VIS framework, while demonstrating state-of-the-art performance. However, VisTR is slow to converge during training, requiring around 1000 GPU hours due to the high computational cost of its transformer attention module. To improve the training efficiency, we propose Deformable VisTR, leveraging spatio-temporal deformable attention module that only attends to a small fixed set of key spatio-temporal sampling points around a reference point. This enables Deformable VisTR to achieve linear computation in the size of spatio-temporal feature maps. Moreover, it can achieve on par performance as the original VisTR with 10× less GPU training hours. We validate the effectiveness of our method on the Youtube-VIS benchmark. Code is available at https://github.com/skrya/DefVIS.

This paper generalizes the Attention in Attention (AiA) mechanism, in P. Fang et al., 2019 by employing explicit mapping in reproducing kernel Hilbert spaces to generate attention values of the input feature map. The AiA mechanism models the capacity of building inter-dependencies among the local and global features by the interaction of inner and outer attention modules. Besides a vanilla AiA module, termed linear attention with AiA, two non-linear counterparts, namely, second-order polynomial attention and Gaussian attention, are also proposed to utilize the non-linear properties of the input features explicitly, via the second-order polynomial kernel and Gaussian kernel approximation. The deep convolutional neural network, equipped with the proposed AiA blocks, is referred to as Attention in Attention Network (AiA-Net). The AiA-Net learns to extract a discriminative pedestrian representation, which combines complementary person appearance and corresponding part features. Extensive ablation studies verify the effectiveness of the AiA mechanism and the use of non-linear features hidden in the feature map for attention design. Furthermore, our approach outperforms current state-of-the-art by a considerable margin across a number of benchmarks. In addition, state-of-the-art performance is also achieved in the video person retrieval task with the assistance of the proposed AiA blocks.

Invertible networks have various benefits for image de-noising since they are lightweight, information-lossless, and memory-saving during back-propagation. However, applying invertible models to remove noise is challenging because the input is noisy, and the reversed output is clean, following two different distributions. We propose an invertible denoising network, InvDN, to address this challenge. InvDN transforms the noisy input into a low-resolution clean image and a latent representation containing noise. To discard noise and restore the clean image, InvDN replaces the noisy latent representation with another one sampled from a prior distribution during reversion. The de-noising performance of InvDN is better than all the existing competitive models, achieving a new state-of-the-art result for the SIDD dataset while enjoying less run time. Moreover, the size of InvDN is far smaller, only having 4.2% of the number of parameters compared to the most recently proposed DANet. Further, via manipulating the noisy latent representation, InvDN is also able to generate noise more similar to the original one. Our code is available at: https://github.com/Yang-Liu1082/InvDN.git.

Self-supervised depth estimation for indoor environments is more challenging than its outdoor counterpart in at least the following two aspects: (i) the depth range of indoor sequences varies a lot across different frames, making it difficult for the depth network to induce consistent depth cues, whereas the maximum distance in outdoor scenes mostly stays the same as the camera usually sees the sky; (ii) the indoor sequences contain much more rotational motions, which cause difficulties for the pose network, while the motions of outdoor sequences are pre-dominantly translational, especially for driving datasets such as KITTI. In this paper, special considerations are given to those challenges and a set of good practices are consolidated for improving the performance of self-supervised monocular depth estimation in indoor environments. The proposed method mainly consists of two novel modules, i.e., a depth factorization module and a residual pose estimation module, each of which is designed to respectively tackle the aforementioned challenges. The effectiveness of each module is shown through a carefully conducted ablation study and the demonstration of the state-of-the-art performance on three indoor datasets, i.e., EuRoC, NYUv2 and 7-Scenes.

Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss. The triplet loss used in video re-ID is usually based on so-called clip features, each aggregated from a few frame features. In this paper, we propose to model the video clip as a set and instead study the distance between sets in the corresponding triplet loss. In contrast to the distance between clip representations, the distance between clip sets considers the pair-wise similarity of each element (i.e., frame representation) between two sets. This allows the network to directly optimize the feature representation at a frame level. Apart from the commonly-used set distance metrics (e.g., ordinary distance and Hausdorff distance), we further propose a hybrid distance metric, tailored for the set-aware triplet loss. Also, we propose a hard positive set construction strategy using the learned class prototypes in a batch. Our proposed method achieves state-of-the-art results across several standard benchmarks, demonstrating the advantages of the proposed method.

In this paper, we focus on exploring the fusion of images and point clouds for 3D object detection in view of the complementary nature of the two modalities, i.e., images possess more semantic information while point clouds specialize in distance sensing. To this end, we present a novel two-stage multi-modal fusion network for 3D object detection, taking both binocular images and raw point clouds as input. The whole architecture facilitates two-stage fusion. The first stage aims at producing 3D proposals through sparse pointwise feature fusion. Within the first stage, we further exploit a joint anchor mechanism that enables the network to utilize 2D-3D classification and regression simultaneously for better proposal generation. The second stage works on the 2D and 3D proposal regions and fuses their dense features. In addition, we propose to use pseudo LiDAR points from stereo matching as a data augmentation method to densify the LiDAR points, as we observe that objects missed by the detection network mostly have too few points especially for far-away objects. Our experiments on the KITTI dataset show that the proposed multi-stage fusion helps the network to learn better representations.

In this paper, we address the problem of inferring the layout of complex road scenes from video sequences. To this end, we formulate it as a top-view road attributes prediction problem and our goal is to predict these attributes for each frame both accurately and consistently. In contrast to prior work, we exploit the following three novel aspects: leveraging camera motions in videos, including context cues and incorporating long-term video information. Specifically, we introduce a model that aims to enforce prediction consistency in videos. Our model consists of one LSTM and one Feature Transform Module (FTM). The former implicitly incorporates the consistency constraint with its hidden states, and the latter explicitly takes the camera motion into consideration when aggregating information along videos. Moreover, we propose to incorporate context information by introducing road participants, e.g. objects, into our model. When the entire video sequence is available, our model is also able to encode both local and global cues, e.g. information from both past and future frames. Experiments on two data sets show that: (1) Incorporating either global or contextual cues improves the prediction accuracy and leveraging both gives the best performance. (2) Introducing the LSTM and FTM modules improves the prediction consistency in videos. (3) The proposed method outperforms the SOTA by a large margin.

Learning matching costs has been shown to be critical to the success of the state-of-the-art deep stereo matching methods, in which 3D convolutions are applied on a 4D feature volume to learn a 3D cost volume. However, this mechanism has never been employed for the optical flow task. This is mainly due to the significantly increased search dimension in the case of optical flow computation, \ie, a straightforward extension would require dense 4D convolutions in order to process a 5D feature volume, which is computationally prohibitive. This paper proposes a novel solution that is able to bypass the requirement of building a 5D feature volume while still allowing the network to learn suitable matching costs from data. Our key innovation is to decouple the connection between 2D displacements and learn the matching costs at each 2D displacement hypothesis independently, \ie, displacement-invariant cost learning. Specifically, we apply the same 2D convolution-based matching net independently on each 2D displacement hypothesis to learn a 4D cost volume. Moreover, we propose a displacement-aware projection layer to scale the learned cost volume, which reconsiders the correlation between different displacement candidates and mitigates the multi-modal problem in the learned cost volume. The cost volume is then projected to optical flow estimation through a 2D soft-argmin layer. Extensive experiments show that our approach achieves state-of-the-art accuracy on various datasets, and outperforms all published optical flow methods on the Sintel benchmark. The code is available at https://github.com/jytime/DICL-Flow.

In this paper, we present LidarStereoNet, the first unsupervised Lidar-stereo fusion network, which can be trained in an end-to-end manner without the need of ground truth depth maps. By introducing a novel ``Feedback Loop'' to connect the network input with output, LidarStereoNet could tackle both noisy Lidar points and misalignment between sensors that have been ignored in existing Lidar-stereo fusion work. Besides, we propose to incorporate the piecewise planar model into the network learning to further constrain depths to conform to the underlying 3D geometry. Extensive quantitative and qualitative evaluations on both real and synthetic datasets demonstrate the superiority of our method, which outperforms state-of-the-art stereo matching, depth completion and Lidar-Stereo fusion approaches significantly.

Unsupervised deep learning for optical flow computation has achieved promising results. Most existing deep-net based methods rely on image brightness consistency and local smoothness constraint to train the networks. Their performance degrades at regions where repetitive textures or occlusions occur. In this paper, we propose Deep Epipolar Flow, an unsupervised optical flow method which incorporates global geometric constraints into network learning. In particular, we investigate multiple ways of enforcing the epipolar constraint in flow estimation. To alleviate a ``chicken-and-egg'' type of problem encountered in dynamic scenes where multiple motions may be present, we propose a low-rank constraint as well as a union-of-subspaces constraint for training. Experimental results on various benchmarking datasets show that our method achieves competitive performance compared with supervised methods and outperforms state-of-the-art unsupervised deep-learning methods.

An exact method of correcting the rolling shutter (RS) effect requires recovering the underlying geometry, i.e. the scene structures and the camera motions between scanlines or between views. However, the multiple-view geometry for RS cameras is much more complicated than its global shutter (GS) counterpart, with various degeneracies. In this paper, we first make a theoretical contribution by showing that RS two-view geometry is degenerate in the case of pure translational camera motion. In view of the complex RS geometry, we then propose a Convolutional Neural Network (CNN)-based method which learns the underlying geometry (camera motion and scene structure) from just a single RS image and perform RS image correction. We call our method structure-and-motion-aware RS correction because it reasons about the concealed motions between the scanlines as well as the scene structure. Our method learns from a large-scale dataset synthesized in a geometrically meaningful way where the RS effect is generated in a manner consistent with the camera motion and scene structure. In extensive experiments, our method achieves superior performance compared to other state-of-the-art methods for single image RS correction and subsequent Structure from Motion (SfM) applications.

Incremental learning using Deep Neural Networks (DNNs) suffers from catastrophic forgetting. Existing methods mitigate it by either storing old image examples or only updating a few fully connected layers of DNNs, which, however, requires large memory footprints or hurts the plasticity of models. In this paper, we propose a new incremental learning strategy based on conditional adversarial networks. Our new strategy allows us to use memory-efficient statistical information to store old knowledge, and fine-tune both convolutional layers and fully connected layers to consolidate new knowledge. Specifically, we propose a model consisting of three parts, i.e., a base sub-net, a generator, and a discriminator. The base sub-net works as a feature extractor which can be pre-trained on large scale datasets and shared across multiple image recognition tasks. The generator conditioned on labeled embeddings aims to construct pseudo-examples with the same distribution as the old data. The discriminator combines real-examples from new data and pseudo-examples generated from the old data distribution to learn representation for both old and new classes. Through adversarial training of the discriminator and generator, we accomplish the multiple continuous incremental learning. Comparison with the state-of-the-arts on public CIFAR-100 and CUB-200 datasets shows that our method achieves the best accuracies on both old and new classes while requiring relatively less memory storage.

We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces. In contrast to previous attempts, our model runs without the aid of spectral clustering. This makes our algorithm one of the kinds that can gracefully scale to large datasets. At its heart, our neural model benefits from a classifier which determines whether a pair of points lies on the same subspace or not. Essential to our model is the construction of two affinity matrices, one from the classifier and the other from a notion of subspace self-expressiveness, to supervise training in a collaborative scheme. We thoroughly assess and contrast the performance of our model against various state-of-the-art clustering algorithms including deep subspace-based ones.

Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems. Inspired by a previous work which solved directly for 3D scene structure by factoring the relative camera poses out, we revisit the principle of “maximizing rigidity” in structure-from-motion literature, and develop a unified theory which is applicable to both rigid and non-rigid structure reconstruction in a rigidity-agnostic way. We formulate these problems as a convex semi-definite program, imposing constraints that seek to apply the principle of minimizing non-rigidity. Our results demonstrate the efficacy of the approach, with stateof- the-art accuracy on various 3D reconstruction problems.

We present a novel deep neural network architecture for unsupervised subspace clustering. This architecture is built upon deep auto-encoders, which non-linearly map the input data into a latent space. Our key idea is to introduce a novel self-expressive layer between the encoder and the decoder to mimic the "self-expressiveness" property that has proven effective in traditional subspace clustering. Being differentiable, our new self-expressive layer provides a simple but effective way to learn pairwise affinities between all data points through a standard back-propagation procedure. Being nonlinear, our neural-network based method is able to cluster data points having complex (often nonlinear) structures. We further propose pre-training and fine-tuning strategies that let us effectively learn the parameters of our subspace clustering networks. Our experiments show that the proposed method significantly outperforms the state-of-the-art unsupervised subspace clustering methods.

Feature tracking is a fundamental problem in computer vision, with applications in many computer vision tasks, such as visual SLAM and action recognition. This paper introduces a novel multi-body feature tracker that exploits a multi-body rigidity assumption to improve tracking robustness under a general perspective camera model. A conventional approach to addressing this problem would consist of alternating between solving two subtasks: motion segmentation and feature tracking under rigidity constraints for each segment. This approach, however, requires knowing the number of motions, as well as assigning points to motion groups, which is typically sensitive to the motion estimates. By contrast, here, we introduce a segmentationfree solution to multi-body feature tracking that bypasses the motion assignment step and reduces to solving a series of subproblems with closed-form solutions. Our experiments demonstrate the benefits of our approach in terms of tracking accuracy and robustness to noise.

The Shape Interaction Matrix (SIM) is one of the earliest approaches to performing subspace clustering (i.e., separating points drawn from a union of subspaces). In this paper, we revisit the SIM and reveal its connections to several recent subspace clustering methods. Our analysis lets us derive a simple, yet effective algorithm to robustify the SIM and make it applicable to realistic scenarios where the data is corrupted by noise. We justify our method by intuitive examples and the matrix perturbation theory. We then show how this approach can be extended to handle missing data, thus yielding an efficient and general subspace clustering algorithm. We demonstrate the benefits of our approach over state-of-the-art subspace clustering methods on several challenging motion segmentation and face clustering problems, where the data includes corruptions and missing measurements.

The problems of motion segmentation and face clustering can be addressed in a framework of subspace clustering methods. In this paper, we tackle the more general problem of clustering data points lying in a union of low-dimensional linear(or affine) subspaces, which can be naturally applied in motion segmentation and face clustering. For data points drawn from linear (or affine) subspaces, we propose a novel algorithm called Null Space Clustering (NSC), utilizing the null space of the data matrix to construct the affinity matrix. To better deal with noise and outliers, it is converted to an equivalent problem with Frobenius norm minimization, which can be solved efficiently. We demonstrate that the proposed NSC leads to improved performance in terms of clustering accuracy and efficiency when compared to state-of-the-art algorithms on two well-known datasets, i.e., Hopkins 155 and Extended Yale B.

In this paper, we tackle the problem of clustering data points drawn from a union of linear (or affine) subspaces. To this end, we introduce an efficient subspace clustering algorithm that estimates dense connections between the points lying in the same subspace. In particular, instead of following the standard compressive sensing approach, we formulate subspace clustering as a Frobenius norm minimization problem, which inherently yields denser con- nections between the data points. While in the noise-free case we rely on the self-expressiveness of the observations, in the presence of noise we simultaneously learn a clean dictionary to represent the data. Our formulation lets us address the subspace clustering problem efficiently. More specifically, the solution can be obtained in closed-form for outlier-free observations, and by performing a series of linear operations in the presence of outliers. Interestingly, we show that our Frobenius norm formulation shares the same solution as the popular nuclear norm minimization approach when the data is free of any noise, or, in the case of corrupted data, when a clean dictionary is learned. Our experimental evaluation on motion segmentation and face clustering demonstrates the benefits of our algorithm in terms of clustering accuracy and efficiency.