Visual localization aims to determine the camera pose of a query image relative to a database of posed images. In recent years, deep neural networks that directly regress camera poses have gained popularity due to their fast inference capabilities. However, existing methods struggle to either generalize well to new scenes or provide accurate camera pose estimates. To address these issues, we present Reloc3r, a simple yet effective visual localization framework. It consists of an elegantly designed relative pose regression network, and a minimalist motion averaging module for absolute pose estimation. Trained on approximately eight million posed image pairs, Reloc3r achieves surprisingly good performance and generalization ability. We conduct extensive experiments on six public datasets, consistently demonstrating the effectiveness and efficiency of the proposed method. It provides high-quality camera pose estimates in real time and generalizes to novel scenes. Code: https://github.com/ffrivera0/reloc3r.

We present HuMoCon, a novel motion-video understanding framework designed for advanced human behavior analysis. The core of our method is a human motion concept discovery framework that efficiently trains multi-modal encoders to extract semantically meaningful and generalizable features. HuMoCon addresses key challenges in motion concept discovery for understanding and reasoning, including the lack of explicit multi-modality feature alignment and the loss of high-frequency information in masked autoencoding frameworks. Our approach integrates a feature alignment strategy that leverages video for contextual understanding and motion for fine-grained interaction modeling, further with a velocity reconstruction mechanism to enhance high-frequency feature expression and mitigate temporal over-smoothing. Comprehensive experiments on standard benchmarks demonstrate that HuMoCon enables effective motion concept discovery and significantly outperforms state-of-the-art methods in training large models for human motion understanding. We will open-source the associated code with our paper.

In this paper, we introduce SLAM3R, a novel and effective system for real-time, high-quality, dense 3D reconstruction using RGB videos. SLAM3R provides an end-to-end solution by seamlessly integrating local 3D reconstruction and global coordinate registration through feed-forward neural networks. Given an input video, the system first converts it into overlapping clips using a sliding window mechanism. Unlike traditional pose optimization-based methods, SLAM3R directly regresses 3D pointmaps from RGB images in each window and progressively aligns and deforms these local pointmaps to create a globally consistent scene reconstruction-all without explicitly solving any camera parameters. Experiments across datasets consistently show that SLAM3R achieves state-of-the-art reconstruction accuracy and completeness while maintaining real-time performance at 20+ FPS. Code available at: https://github.com/PKU-VCL-3DV/SLAM3R.

Policy learning through behavior cloning poses significant challenges, particularly when demonstration data is limited. In this work, we present HyPoGen, a novel optimization-biased hypernetwork for policy generation. The proposed hypernetwork learns to synthesize optimal policy parameters solely from task specifications -- without accessing training data -- by modeling policy generation as an approximation of the optimization process executed over a finite number of steps and assuming these specifications serve as a sufficient representation of the demonstration data. By incorporating structural designs that bias the hypernetwork towards optimization, we can improve its generalization capability while only training on source task demonstrations. During the feed-forward prediction pass, the hypernetwork effectively performs an optimization in the latent (compressed) policy space, which is then decoded into policy parameters for action prediction. Experimental results on locomotion and manipulation benchmarks show that HyPoGen significantly outperforms state-of-the-art methods in generating policies for unseen target tasks without any demonstrations, achieving higher success rates and underscoring the potential of optimization-biased hypernetworks in advancing generalizable policy generation. Our code and data are available at: https://github.com/ReNginx/HyPoGen.

3D Gaussians, as an explicit scene representation, typically involve thousands to millions of elements per scene. This makes it challenging to control the scene in ways that reflect the underlying semantics, where the number of independent entities is typically much smaller. Especially, if one wants to animate or edit objects in the scene, as this requires coordination among the many Gaussians involved in representing each object. To address this issue, we develop a mutual information shaping technique that enforces resonance and coordination between correlated Gaussians via a Gaussian attribute decoding network. Such correlations can be learned from putative 2D object masks in different views. By approximating the mutual information with the gradients concerning the network parameters, our method ensures consistency between scene elements and enables efficient scene editing by operating on network parameters rather than massive Gaussians. In particular, we develop an effective learning pipeline named ***InfoGS*** with lightweight optimization to shape the attribute decoding network ,while ensuring that the shaping (consistency) is maintained during continuous edits, avoiding re-shaping after parameter changes. Notably, our training only touches a small fraction of all Gaussians in the scene yet attains the desired correlated behavior according to the underlying scene structure. The proposed technique is evaluated on challenging scenes and demonstrates significant performance improvements in 3D object segmentation and promoting scene interactions, while inducing low computation and memory requirements. Our code is available at: https://github.com/StylesZhang/InfoGS.

Training embodied agents to perform complex robotic tasks presents significant challenges due to the entangled factors of task compositionality, environmental diversity, and dynamic changes. In this work, we introduce a novel imitation learning framework to train closed-loop concept-guided policies that enhance long-horizon task performance by leveraging discovered manipulation concepts. Unlike methods that rely on predefined skills and human-annotated labels, our approach allows agents to autonomously abstract manipulation concepts from their proprioceptive states, thereby alleviating misalignment due to ambiguities in human semantics and environmental complexity. Our framework comprises two primary components: an *Automatic Concept Discovery* module that identifies meaningful and consistent manipulation concepts, and a *Concept-Guided Policy Learning* module that effectively utilizes these manipulation concepts for adaptive task execution, including a *Concept Selection Transformer* for concept-based guidance and a *Concept-Guided Policy* for action prediction with the selected concepts. Experiments demonstrate that our approach significantly outperforms baseline methods across a range of tasks and environments, while showcasing emergent consistency in motion patterns associated with the discovered manipulation concepts. Codes are available at: https://github.com/PeiZhou26/AutoCGP.

Eye gaze offers valuable cues about attention, short-term intent, and future actions, making it a powerful signal for modeling egocentric behavior. In this work, we propose a gaze-regularized framework that enhances VLMs for two key egocentric understanding tasks: fine-grained future event prediction and current activity understanding. Unlike prior approaches that rely solely on visual inputs or use gaze as an auxiliary input signal , our method uses gaze only during training. We introduce a gaze-regularized attention mechanism that aligns model focus with human visual gaze. This design is flexible and modular, allowing it to generalize across multiple VLM architectures that utilize attention. Experimental results show that our approach improves semantic prediction scores by up to 11$\%$ for future event prediction and around 7$\%$ for current activity understanding, compared to the corresponding baseline models trained without gaze regularization. These results highlight the value of gaze-guided training in improving the accuracy and robustness of egocentric VLMs. Overall, this work establishes a foundation for using human gaze to enhance the predictive capabilities of VLMs in real-world scenarios like assistive robots and human-machine collaboration. Code and additional information is available at: https://github.com/anupampani/Gaze-VLM

We focus on the self-supervised discovery of manipulation concepts that can be adapted and reassembled to address various robotic tasks. We propose that the decision to conceptualize a physical procedure should not depend on how we name it (semantics) but rather on the significance of the informativeness in its representation regarding the low-level physical state and state changes. We model manipulation concepts -- discrete symbols -- as generative and discriminative goals and derive metrics that can autonomously link them to meaningful sub-trajectories from noisy, unlabeled demonstrations. Specifically, we employ a trainable codebook containing encodings --symbols -- capable of synthesizing the end-state of a sub-trajectory given the current state (generative informativeness). Moreover, the encoding corresponding to a particular sub-trajectory should differentiate the state within and outside it and confidently predict the subsequent action based on the gradient of its discriminative score (discriminative informativeness). These metrics, which do not rely on human annotation, can be seamlessly integrated into a VQ-VAE framework, enabling the partitioning of demonstrations into semantically consistent sub-trajectories, fulfilling the purpose of discovering manipulation concepts and the corresponding (sub)-goal states. We evaluate the effectiveness of the learned concepts by training policies that utilize them as guidance, demonstrating superior performance compared to other baselines. Additionally, our discovered manipulation concepts compare favorably to human-annotated ones, while saving much manual effort. The code and trained models will be made public.

Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To address this, we introduce Text2Reward, a data-free framework that automates the generation and shaping of dense reward functions based on large language models (LLMs). Given a goal described in natural language, Text2Reward generates shaped dense reward functions as an executable program grounded in a compact representation of the environment. Unlike inverse RL and recent work that uses LLMs to write sparse reward codes or unshaped dense rewards with a constant function across timesteps, Text2Reward produces interpretable, free-form dense reward codes that cover a wide range of tasks, utilize existing packages, and allow iterative refinement with human feedback. We evaluate Text2Reward on two robotic manipulation benchmarks (ManiSkill2, MetaWorld) and two locomotion environments of MuJoCo. On 13 of the 17 manipulation tasks, policies trained with generated reward codes achieve similar or better task success rates and convergence speed than expert-written reward codes. For locomotion tasks, our method learns six novel locomotion behaviors with a success rate exceeding 94%. Furthermore, we show that the policies trained in the simulator with our method can be deployed in the real world. Finally, Text2Reward further improves the policies by refining their reward functions with human feedback. Video results are available at https://text-to-reward.github.io/

Estimating mutual correlations between random variables or data streams is essential for intelligent behavior and decision-making. As a fundamental quantity for measuring statistical relationships, mutual information has been extensively studied and utilized for its generality and equitability. However, existing methods often lack the efficiency needed for real-time applications, such as test-time optimization of a neural network, or the differentiability required for end-to-end learning, like histograms. We introduce a neural network called InfoNet, which directly outputs mutual information estimations of data streams by leveraging the attention mechanism and the computational efficiency of deep learning infrastructures. By maximizing a dual formulation of mutual information through large-scale simulated training, our approach circumvents time-consuming test-time optimization and offers generalization ability. We evaluate the effectiveness and generalization of our proposed mutual information estimation scheme on various families of distributions and applications. Our results demonstrate that InfoNet and its training process provide a graceful efficiency-accuracy trade-off and order-preserving properties. We will make the code and models available as a comprehensive toolbox to facilitate studies in different fields requiring real-time mutual information estimation.

Despite significant progress in robotics and embodied AI in recent years, deploying robots for long-horizon tasks remains a great challenge. Majority of prior arts adhere to an open-loop philosophy and lack real-time feedback, leading to error accumulation and undesirable robustness. A handful of approaches have endeavored to establish feedback mechanisms leveraging pixel-level differences or pre-trained visual representations, yet their efficacy and adaptability have been found to be constrained. Inspired by classic closed-loop control systems, we propose CLOVER, a closed-loop visuomotor control framework that incorporates feedback mechanisms to improve adaptive robotic control. CLOVER consists of a text-conditioned video diffusion model for generating visual plans as reference inputs, a measurable embedding space for accurate error quantification, and a feedback-driven controller that refines actions from feedback and initiates replans as needed. Our framework exhibits notable advancement in real-world robotic tasks and achieves state-of-the-art on CALVIN benchmark, improving by 8% over previous open-loop counterparts. Code and checkpoints are maintained at https://github.com/OpenDriveLab/CLOVER.

Recent advancements in models linking natural language with human motions have shown significant promise in motion generation and editing based on instructional text. Motivated by applications in sports coaching and motor skill learning, we investigate the inverse problem: generating corrective instructional text, leveraging motion editing and generation models. We introduce a novel approach that, given a user’s current motion (source) and the desired motion (target), generates text instructions to guide the user towards achieving the target motion. We leverage large language models to generate corrective texts and utilize existing motion generation and editing frameworks to compile datasets of triplets (source motion, target motion, and corrective text). Using this data, we propose a new motion-language model for generating corrective instructions. We present both qualitative and quantitative results across a diverse range of applications that largely improve upon baselines. Our approach demonstrates its effectiveness in instructional scenarios, offering text-based guidance to correct and enhance user performance.

One-light-at-a-time (OLAT) images sample a broader range of object appearance changes than images captured under constant lighting and are superior as input to object relighting. Although existing methods have produced reasonable relighting quality using OLAT images, they utilize surface-like representations, limiting their capacity to model volumetric objects, such as furs. Besides, their rendering process is time-consuming and still far from being used in real-time applications. To address these issues, we propose OLAT Gaussians to build relightable representations of objects from multiview OLAT images. We build our pipeline on 3D Gaussian Splatting (3DGS), which achieves real-time high-quality rendering. To augment 3DGS with relighting capability, we assign each Gaussian a learnable feature vector, serving as an index to query the objects’ appearance field. Specifically, we decompose the appearance field into an incident illumination function and a scattering function. The former accounts for light transmittance and foreshortening effects, while the latter represents the object’s material properties to scatter light. Rather than using an off-the-shelf physically-based parametric rendering formulation, we model both functions using multi-layer perceptrons (MLPs). This makes our method suitable for various objects, e.g., opaque surfaces, semi-transparent volumes, furs, fabrics, etc. Given a camera view and a point light position, we compute each Gaussian’s color as the product of the light intensity, the incident illumination value, and the scattering value, and then render the target image through the 3DGS rasterizer. To enhance rendering quality, we further utilize a proxy mesh to provide OLAT Gaussians with normals to improve highlights and visibility cues to improve shadows. Extensive experiments demonstrate that our method produces state-of-the-art rendering quality with significantly more details in texture-rich areas than previous methods. Our method also achieves real-time rendering, allowing users to interactively modify camera views and point light positions to get immediate rendering results, which are not available from the offline rendering of previous methods.

We propose a method that trains a neural radiance field (NeRF) to encode not only the appearance of the scene but also semantic correlations between scene points, regions, or entities - aiming to capture their mutual co-variation patterns. In contrast to the traditional first-order photometric reconstruction objective, our method explicitly regularizes the learning dynamics to align the Jacobians of highly-correlated entities, which proves to maximize the mutual information between them under random scene perturbations. By paying attention to this second-order information, we can shape a NeRF to express semantically meaningful synergies when the network weights are changed by a delta along the gradient of a single entity, region, or even a point. To demonstrate the merit of this mutual information modeling, we leverage the coordinated behavior of scene entities that emerges from our shaping to perform label propagation for semantic and instance segmentation. Our experiments show that a JacobiNeRF is more efficient in propagating annotations among 2D pixels and 3D points compared to NeRFs without mutual information shaping, especially in extremely sparse label regimes - thus reducing annotation burden. The same machinery can further be used for entity selection or scene modifications. Our code is available at https://github.com/xxm19/jacobinerf.

We propose VDN-NeRF, a method to train neural radiance fields (NeRFs) for better geometry under non-Lambertian surface and dynamic lighting conditions that cause significant variation in the radiance of a point when viewed from different angles. Instead of explicitly modeling the underlying factors that result in the view-dependent phenomenon, which could be complex yet not inclusive, we develop a simple and effective technique that normalizes the view-dependence by distilling invariant information already encoded in the learned NeRFs. We then jointly train NeRFs for view synthesis with view-dependence normalization to attain quality geometry. Our experiments show that even though shape-radiance ambiguity is inevitable, the proposed normalization can minimize its effect on geometry, which essentially aligns the optimal capacity needed for explaining view-dependent variations. Our method applies to various baselines and significantly improves geometry without changing the volume rendering pipeline, even if the data is captured under a moving light source. Code is available at: https://github.com/BoifZ/VDN-NeRF.

We propose a novel and efficient method for reconstructing manifold surfaces from point clouds. Unlike previous approaches that use dense implicit reconstructions or piecewise approximations and overlook inherent structures like quadrics in CAD models, our method faithfully preserves these quadric structures by assembling primitives. To achieve high-quality primitive extraction, we use a variational shape approximation, followed by a mesh arrangement for space partitioning and candidate primitive patches generation. We then introduce an effective pruning mechanism to classify candidate primitive patches as active or inactive, and further prune inactive patches to reduce the search space and speed up surface extraction significantly. Finally, the optimal active patches are computed by a binary linear programming and assembled as manifold and watertight surfaces. We perform extensive experiments on a wide range of CAD objects to validate its effectiveness.

The ability to forecast human-environment collisions from egocentric observations is vital to enable collision avoidance in applications such as VR, AR, and wearable assistive robotics. In this work, we introduce the challenging problem of predicting collisions in diverse environments from multi-view egocentric videos captured from body-mounted cameras. Solving this problem requires a generalizable perception system that can classify which human body joints will collide and estimate a collision region heatmap to localize collisions in the environment. To achieve this, we propose a transformer-based model called COPILOT to perform collision prediction and localization simultaneously, which accumulates information across multi-view inputs through a novel 4D space-time-viewpoint attention mechanism. To train our model and enable future research on this task, we develop a synthetic data generation framework that produces egocentric videos of virtual humans moving and colliding within diverse 3D environments. This framework is then used to establish a large-scale dataset consisting of 8.6M egocentric RGBD frames. Extensive experiments show that COPILOT generalizes to unseen synthetic as well as real-world scenes. We further demonstrate COPILOT outputs are useful for downstream collision avoidance through simple closed-loop control. Please visit our project webpage at https://sites.google.com/stanford.edu/copilot.

Some extremely low-dimensional yet crucial geometric eigen-lengths often determine the success of some geometric tasks. For example, the *height* of an object is important to measure to check if it can fit between the shelves of a cabinet, while the *width* of a couch is crucial when trying to move it through a doorway. Humans have materialized such crucial geometric eigen-lengths in common sense since they are very useful in serving as succinct yet effective, highly interpretable, and universal object representations. However, it remains obscure and underexplored if learning systems can be equipped with similar capabilities of automatically discovering such key geometric quantities from doing tasks. In this work, we therefore for the first time formulate and propose a novel learning problem on this question and set up a benchmark suite including tasks, data, and evaluation metrics for studying the problem. We focus on a family of common fitting tasks as the testbed for the proposed learning problem. We explore potential solutions and demonstrate the feasibility of learning eigen-lengths from simply observing successful and failed fitting trials. We also attempt geometric grounding for more accurate eigen-length measurement and study the reusability of the learned geometric eigen-lengths across multiple tasks. Our work marks the first exploratory step toward learning crucial geometric eigen-lengths and we hope it can inspire future research in tackling this important yet underexplored problem.

We describe a method to deal with performance drop in semantic segmentation caused by viewpoint changes within multi-camera systems, where temporally paired images are readily available, but the annotations may only be abundant for a few typical views. Existing methods alleviate performance drop via domain alignment in a shared space and assume that the mapping from the aligned space to the output is transferable. However, the novel content induced by viewpoint changes may nullify such a space for effective alignments, thus resulting in negative adaptation. Our method works without aligning any statistics of the images between the two domains. Instead, it utilizes a novel attention-based view transformation network trained only on color images to hallucinate the semantic images for the target. Despite the lack of supervision, the view transformation network can still generalize to semantic images thanks to the induced “information transport” bias. Furthermore, to resolve ambiguities in converting the semantic images to semantic labels, we treat the view transformation network as a functional representation of an unknown mapping implied by the color images and propose functional label hallucination to generate pseudo-labels with uncertainties in the target domains. Our method surpasses baselines built on state-of-the-art correspondence estimation and view synthesis methods. Moreover, it outperforms the state-of-the-art unsupervised domain adaptation methods that utilize self-training and adversarial domain alignments. Our code and dataset will be made publicly available.

As a popular geometric representation, point clouds have attracted much attention in 3D vision, leading to many applications in autonomous driving and robotics. One important yet unsolved issue for learning on point cloud is that point clouds of the same object can have significant geometric variations if generated using different procedures or captured using different sensors. These inconsistencies induce domain gaps such that neural networks trained on one domain may fail to generalize on others. A typical technique to reduce the domain gap is to perform adversarial training so that point clouds in the feature space can align. However, adversarial training is easy to fall into degenerated local minima, resulting in negative adaptation gains. Here we propose a simple yet effective method for unsupervised domain adaptation on point clouds by employing a self-supervised task of learning geometry-aware implicits, which plays two critical roles in one shot. First, the geometric information in the point clouds is preserved through the implicit representations for downstream tasks. More importantly, the domain-specific variations can be effectively learned away in the implicit space. We also propose an adaptive strategy to compute unsigned distance fields for arbitrary point clouds due to the lack of shape models in practice. When combined with a task loss, the proposed outperforms state-of-the-art unsupervised domain adaptation methods that rely on adversarial domain alignment and more complicated self-supervised tasks. Our method is evaluated on both PointDA-10 and GraspNet datasets. Code and data are available at: https://github.com/Jhonve/ImplicitPCDA.

We describe an unsupervised method to detect and segment portions of images of live scenes that, at some point in time, are seen moving as a coherent whole, which we refer to as objects. Our method first partitions the motion field by minimizing the mutual information between segments. Then, it uses the segments to learn object models that can be used for detection in a static image. Static and dynamic models are represented by deep neural networks trained jointly in a bootstrapping strategy, which enables extrapolation to previously unseen objects. While the training process requires motion, the resulting object segmentation network can be used on either static images or videos at inference time. As the volume of seen videos grows, more and more objects are seen moving, priming their detection, which then serves as a regularizer for new objects, turning our method into unsupervised continual learning to segment objects. Our models are compared to the state of the art in both video object segmentation and salient object detection. In the six benchmark datasets tested, our models compare favorably even to those using pixel-level supervision, despite requiring no manual annotation.

We propose an architecture and training scheme to predict video frames by explicitly modeling dis-occlusions and capturing the evolution of semantically consistent regions in the video. The scene layout (semantic map) and motion (optical flow) are decomposed into layers, which are predicted and fused with their context to generate future layouts and motions. The appearance of the scene is warped from past frames using the predicted motion in co-visible regions; dis-occluded regions are synthesized with content-aware inpainting utilizing the predicted scene layout. The result is a predictive model that explicitly represents objects and learns their class-specific motion, which we evaluate on video prediction benchmarks.

We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other. We illustrate the method in semantic segmentation, where densely annotated images are aplenty in one domain (synthetic data), but difficult to obtain in another (real images). Current state-of-the-art methods are complex, some requiring adversarial optimization to render the backbone of a neural network invariant to the discrete domain selection variable. Our method does not require any training to perform the domain alignment, just a simple Fourier Transform and its inverse. Despite its simplicity, it achieves state-of-the-art performance in the current benchmarks, when integrated into a relatively standard semantic segmentation model. Our results indicate that even simple procedures can discount nuisance variability in the data that more sophisticated methods struggle to learn away.

We describe a method to train a generative model with latent factors that are (approximately) independent and localized. This means that perturbing the latent variables affects only local regions of the synthesized image, corresponding to objects. Unlike other unsupervised generative models, ours enables object-centric manipulation, without requiring object-level annotations, or any form of annotation for that matter. The key to our method is the combination of spatial disentanglement, enforced by a Contextual Information Separation loss, and perceptual cycle-consistency, enforced by a loss that penalizes changes in the image partition in response to perturbations of the latent factors. We test our method's ability to allow independent control of spatial and semantic factors of variability on existing datasets and also introduce two new ones that highlight the limitations of current methods.

We introduce two criteria to regularize the optimization involved in learning a classifier in a domain where no annotated data are available, leveraging annotated data in a different domain, a problem known as unsupervised domain adaptation. We focus on the task of semantic segmentation, where annotated synthetic data are aplenty, but annotating real data is laborious. The first criterion, inspired by visual psychophysics, is that the map between the two image domains be phase-preserving. This restricts the set of possible learned maps, while enabling enough flexibility to transfer semantic information. The second criterion aims to leverage ecological statistics, or regularities in the scene which are manifest in any image of it, regardless of the characteristics of the illuminant or the imaging sensor. It is implemented using a deep neural network that scores the likelihood of each possible segmentation given a single un-annotated image. Incorporating these two priors in a standard domain adaptation framework improves performance across the board in the most common unsupervised domain adaptation benchmarks for semantic segmentation.

We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another network attempts to make such context as uninformative as possible. The result is a model where hypotheses naturally compete with no need for explicit regularization or hyper-parameter tuning. Although our method requires no supervision whatsoever, it outperforms several methods that are pre-trained on large annotated datasets. Our model can be thought of as a generalization of classical variational generative region-based segmentation, but in a way that avoids explicit regularization or solution of partial differential equations at run-time.

We present a deep learning system to infer the posterior distribution of a dense depth map associated with an image, by exploiting sparse range measurements, for instance from a lidar. While the lidar may provide a depth value for a small percentage of the pixels, we exploit regularities reflected in the training set to complete the map so as to have a probability over depth for each pixel in the image. We exploit a Conditional Prior Network, that allows associating a probability to each depth value given an image, and combine it with a likelihood term that uses the sparse measurements. Optionally we can also exploit the availability of stereo during training, but in any case only require a single image and a sparse point cloud at run-time. We test our approach on both unsupervised and supervised depth completion using the KITTI benchmark, and improve the state-of-the-art in both.

We introduce a method to compute optical flow at multiple scales of motion, without resorting to multi-resolution or combinatorial methods. It addresses the key problem of small objects moving fast, and resolves the artificial binding between how large an object is and how fast it can move before being diffused away by classical scale-space. Even with no learning, it achieves top performance on the most challenging optical flow benchmark. Moreover, the results are interpretable, and indeed we list the assumptions underlying our method explicitly. The key to our approach is the matching progression from slow to fast, as well as the choice of in-terpolation method, or equivalently the prior, to fill in regions where the data allows it. We use several off-the-shelf components, with relatively low sensitivity to parameter tuning. Computational cost is comparable to the state-of-the-art.

We present a new approach to wide baseline matching. We propose to use a hierarchical decomposition of the image domain and coarse-to-fine selection of regions to match. In contrast to interest point matching methods, which sample salient regions to reduce the cost of comparing all regions in two images, our method eliminates regions systematically to achieve efficiency. One advantage of our approach is that it is not restricted to covariant salient regions, which is too restrictive under large viewpoint and leads to few corresponding regions. Affine invariant matching of regions in the hierarchy is achieved efficiently by a coarse-to-fine search of the affine space. Experiments on two benchmark datasets shows that our method finds more correct correspondence of the image (with fewer false alarms) than other wide baseline methods on large viewpoint change.

We propose a method to detect disocclusion in video sequences of three-dimensional scenes and to partition the disoccluded regions into objects, defined by coherent deformation corresponding to surfaces in the scene. Our method infers deformation fields that are piecewise smooth by construction without the need for an explicit regularizer and the associated choice of weight. It then partitions the disoccluded region and groups its components with objects by leveraging on the complementarity of motion and appearance cues: Where appearance changes within an object, motion can usually be reliably inferred and used for grouping. Where appearance is close to constant, it can be used for grouping directly. We integrate both cues in an energy minimization framework, incorporate prior assumptions explicitly into the energy, and propose a numerical scheme.

We present a method to track the shape of an object from video. The method uses a joint shape and appearance model of the object, which is propagated to match shape and radiance in subsequent frames, determining object shape. Self-occlusions and dis-occlusions of the object from camera and object motion pose difficulties to joint shape and appearance models in tracking. They are unable to adapt to new shape and appearance information, leading to inaccurate shape detection. In this work, we model self-occlusions and dis-occlusions in a joint shape and appearance tracking framework. Self-occlusions and the warp to propagate the model are coupled, thus we formulate a joint optimization problem. We derive a coarse-to-fine optimization method, advantageous in tracking, that initially perturbs the model by coarse perturbations before transitioning to finer-scale perturbations seamlessly. This coarse-to-fine behavior is automatically induced by gradient descent on a novel infinite-dimensional Riemannian manifold that we introduce. The manifold consists of planar parameterized regions, and the metric that we introduce is a novel Sobolev metric. Experiments on video exhibiting occlusions/dis-occlusions, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy.

We present a method to track the precise shape of a dynamic object in video. Joint dynamic shape and appearance models, in which a template of the object is propagated to match the object shape and radiance in the next frame, are advantageous over methods employing global image statistics in cases of complex object radiance and cluttered background. In cases of complex 3D object motion and relative viewpoint change, self-occlusions and dis-occlusions of the object are prominent, and current methods employing joint shape and appearance models are unable to accurately adapt to new shape and appearance information, leading to inaccurate shape detection. In this work, we model self-occlusions and dis-occlusions in a joint shape and appearance tracking framework. Experiments on video exhibiting occlusion/dis-occlusion, complex radiance and background show that occlusion/dis-occlusion modeling leads to superior shape accuracy compared to recent methods employing joint shape/appearance models or employing global statistics.