arXiv subjects

Angjoo Kanazawa

Publications and source records attributed to Angjoo Kanazawa.

At least 37 records · Page 2Linked to original sources

arXiv2026

Human-level 3D shape perception emerges from multi-view learning

Humans can infer the three-dimensional structure of objects from two-dimensional visual inputs. Modeling this ability has been a longstanding goal for the science and engineering of visual intelligence, yet decades of computational methods have fallen short of human performance. Here we develop a modeling framework that predicts human 3D shape inferences for arbitrary objects, directly from experimental stimuli. We achieve this with a novel class of neural networks trained using a visual-spatial objective over naturalistic sensory data; given a set of images taken from different locations within a natural scene, these models learn to predict spatial information related to these images, such as camera location and visual depth, without relying on any object-related inductive biases. Notably, these visual-spatial signals are analogous to sensory cues readily available to humans. We design a zero-shot evaluation approach to determine the performance of these 'multi-view' models on a well established 3D perception task, then compare model and human behavior. Our modeling framework is the first to match human accuracy on 3D shape inferences, even without task-specific training or fine-tuning. Remarkably, independent readouts of model responses predict fine-grained measures of human behavior, including error patterns and reaction times, revealing a natural correspondence between model dynamics and human perception. Taken together, our findings indicate that human-level 3D perception can emerge from a simple, scalable learning objective over naturalistic visual-spatial data. Code, images, and human data needed to reproduce all analyses can be found at https://tzler.github.io/human_multiview/

cs.CV↗

arXiv2026

Diffusion Forcing for Multi-Agent Interaction Sequence Modeling

Understanding and generating multi-person interactions is a fundamental challenge with broad implications for robotics and social computing. While humans naturally coordinate in groups, modeling such interactions remains difficult due to long temporal horizons, strong inter-agent dependencies, and variable group sizes. Existing motion generation methods are largely task-specific and do not generalize to flexible multi-agent generation. We introduce MAGNet (Multi-Agent Generative Network), a unified autoregressive diffusion framework for multi-agent motion generation that supports a wide range of interaction tasks through flexible conditioning and sampling. MAGNet performs dyadic and polyadic prediction, partner inpainting, partner prediction, and agentic generation all within a single model, and can autoregressively generate ultra-long sequences spanning hundreds of motion steps. We explicitly model inter-agent coupling during autoregressive denoising, enabling coherent coordination across agents. As a result, MAGNet captures both tightly synchronized activities (e.g., dancing, boxing) and loosely structured social interactions. Our approach performs on par with specialized methods on dyadic benchmarks while naturally extending to polyadic scenarios involving three or more interacting people. Please watch the supplemental video, where the temporal dynamics and spatial coordination of generated interactions are best appreciated. Project page: https://von31.github.io/MAGNet/

cs.CV↗

arXiv2026

Fillerbuster: Unified Generative Scene Completion Model for Casual Captures

We present Fillerbuster, a unified model that completes unknown regions of a 3D scene with a multi-view latent diffusion transformer. Casual captures are often sparse and miss surrounding content behind objects or above the scene. Existing methods are not suitable for this challenge as they focus on making known pixels look good with sparse-view priors, or on creating missing sides of objects from just one or two photos. In reality, we often have hundreds of input frames and want to complete areas that are missing and unobserved from the input frames. Our solution is to train a generative model that can consume a large context of input frames while generating unknown target views and recovering image poses when camera parameters are unknown. We show results where we complete partial captures on two existing datasets. We also present an uncalibrated scene completion task where our unified model predicts both poses and creates new content. We open-source our framework for integration into popular reconstruction platforms like Nerfstudio or Gsplat. We present a flexible, unified inpainting framework to predict many images and poses together, where all inputs are jointly inpainted, and it could be extended to predict more modalities such as depth.

cs.CV↗

arXiv2026

Visually Prompted Benchmarks Are Surprisingly Fragile

A key challenge in evaluating VLMs is testing models' ability to analyze visual content independently from their textual priors. Recent benchmarks such as BLINK probe visual perception through visual prompting, where questions about visual content are paired with coordinates to which the question refers, with the coordinates explicitly marked in the image itself. While these benchmarks are an important part of VLM evaluation, we find that existing models are surprisingly fragile to seemingly irrelevant details of visual prompting: simply changing a visual marker from red to blue can completely change rankings among models on a leaderboard. By evaluating nine commonly-used open- and closed-source VLMs on two visually prompted tasks, we demonstrate how details in benchmark setup, including visual marker design and dataset size, have a significant influence on model performance and leaderboard rankings. These effects can even be exploited to lift weaker models above stronger ones; for instance, slightly increasing the size of the visual marker results in open-source InternVL3-8B ranking alongside or better than much larger proprietary models like Gemini 2.5 Pro. We further show that low-level inference choices that are often ignored in benchmarking, such as JPEG compression levels in API calls, can also cause model lineup changes. These details have substantially larger impacts on visually prompted benchmarks than on conventional semantic VLM evaluations. To mitigate this instability, we curate existing datasets to create VPBench, a larger visually prompted benchmark with 16 visual marker variants. We open-source VPBench and our analysis framework at: https://lisadunlap.github.io/vpbench/.

cs.CV↗

arXiv2025

Cameras as Relative Positional Encoding

Transformers are increasingly prevalent for multi-view computer vision tasks, where geometric relationships between viewpoints are critical for 3D perception. To leverage these relationships, multi-view transformers must use camera geometry to ground visual tokens in 3D space. In this work, we compare techniques for conditioning transformers on cameras: token-level raymap encodings, attention-level relative pose encodings, and a new relative encoding we propose -- Projective Positional Encoding (PRoPE) -- that captures complete camera frustums, both intrinsics and extrinsics, as a relative positional encoding. Our experiments begin by showing how relative camera conditioning improves performance in feedforward novel view synthesis, with further gains from PRoPE. This holds across settings: scenes with both shared and varying intrinsics, when combining token- and attention-level conditioning, and for generalization to inputs with out-of-distribution sequence lengths and camera intrinsics. We then verify that these benefits persist for different tasks, stereo depth estimation and discriminative spatial cognition, as well as larger model sizes.

cs.CV↗

arXiv2025

TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System

Large-scale data has driven breakthroughs in robotics, from language models to vision-language-action models in bimanual manipulation. However, humanoid robotics lacks equally effective data collection frameworks. Existing humanoid teleoperation systems either use decoupled control or depend on expensive motion capture setups. We introduce TWIST2, a portable, mocap-free humanoid teleoperation and data collection system that preserves full whole-body control while advancing scalability. Our system leverages PICO4U VR for obtaining real-time whole-body human motions, with a custom 2-DoF robot neck (cost around $250) for egocentric vision, enabling holistic human-to-humanoid control. We demonstrate long-horizon dexterous and mobile humanoid skills and we can collect 100 demonstrations in 15 minutes with an almost 100% success rate. Building on this pipeline, we propose a hierarchical visuomotor policy framework that autonomously controls the full humanoid body based on egocentric vision. Our visuomotor policy successfully demonstrates whole-body dexterous manipulation and dynamic kicking tasks. The entire system is fully reproducible and open-sourced at https://yanjieze.com/TWIST2 . Our collected dataset is also open-sourced at https://twist-data.github.io .

cs.RO↗

arXiv2025

Shape of Motion: 4D Reconstruction from a Single Video

Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches depend on templates, are effective only in quasi-static scenes, or fail to model 3D motion explicitly. We introduce a method for reconstructing generic dynamic scenes, featuring explicit, persistent 3D motion trajectories in the world coordinate frame, from casually captured monocular videos. We tackle the problem with two key insights: First, we exploit the low-dimensional structure of 3D motion by representing scene motion with a compact set of SE(3) motion bases. Each point's motion is expressed as a linear combination of these bases, facilitating soft decomposition of the scene into multiple rigidly-moving groups. Second, we take advantage of off-the-shelf data-driven priors such as monocular depth maps and long-range 2D tracks, and devise a method to effectively consolidate these noisy supervisory signals, resulting in a globally consistent representation of the dynamic scene. Experiments show that our method achieves state-of-the-art performance for both long-range 3D/2D motion estimation and novel view synthesis on dynamic scenes. Project Page: https://shape-of-motion.github.io/

cs.CV↗

arXiv2025

Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop

Humans do not passively observe the visual world -- we actively look in order to act. Motivated by this principle, we introduce EyeRobot, a robotic system with gaze behavior that emerges from the need to complete real-world tasks. We develop a mechanical eyeball that can freely rotate to observe its surroundings and train a gaze policy to control it using reinforcement learning. We accomplish this by first collecting teleoperated demonstrations paired with a 360 camera. This data is imported into a simulation environment that supports rendering arbitrary eyeball viewpoints, allowing episode rollouts of eye gaze on top of robot demonstrations. We then introduce a BC-RL loop to train the hand and eye jointly: the hand (BC) agent is trained from rendered eye observations, and the eye (RL) agent is rewarded when the hand produces correct action predictions. In this way, hand-eye coordination emerges as the eye looks towards regions which allow the hand to complete the task. EyeRobot implements a foveal-inspired policy architecture allowing high resolution with a small compute budget, which we find also leads to the emergence of more stable fixation as well as improved ability to track objects and ignore distractors. We evaluate EyeRobot on five panoramic workspace manipulation tasks requiring manipulation in an arc surrounding the robot arm. Our experiments suggest EyeRobot exhibits hand-eye coordination behaviors which effectively facilitate manipulation over large workspaces with a single camera. See project site for videos: https://www.eyerobot.net/

cs.RO↗

arXiv2025

Visual Imitation Enables Contextual Humanoid Control

How can we teach humanoids to climb staircases and sit on chairs using the surrounding environment context? Arguably, the simplest way is to just show them-casually capture a human motion video and feed it to humanoids. We introduce VIDEOMIMIC, a real-to-sim-to-real pipeline that mines everyday videos, jointly reconstructs the humans and the environment, and produces whole-body control policies for humanoid robots that perform the corresponding skills. We demonstrate the results of our pipeline on real humanoid robots, showing robust, repeatable contextual control such as staircase ascents and descents, sitting and standing from chairs and benches, as well as other dynamic whole-body skills-all from a single policy, conditioned on the environment and global root commands. VIDEOMIMIC offers a scalable path towards teaching humanoids to operate in diverse real-world environments.

cs.RO↗

arXiv2025

Flow Matching Policy Gradients

Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm that brings flow matching into the policy gradient framework. FPO casts policy optimization as maximizing an advantage-weighted ratio computed from the conditional flow matching loss, in a manner compatible with the popular PPO-clip framework. It sidesteps the need for exact likelihood computation while preserving the generative capabilities of flow-based models. Unlike prior approaches for diffusion-based reinforcement learning that bind training to a specific sampling method, FPO is agnostic to the choice of diffusion or flow integration at both training and inference time. We show that FPO can train diffusion-style policies from scratch in a variety of continuous control tasks. We find that flow-based models can capture multimodal action distributions and achieve higher performance than Gaussian policies, particularly in under-conditioned settings.

cs.LG↗

arXiv2025

Viser: Imperative, Web-based 3D Visualization in Python

We present Viser, a 3D visualization library for computer vision and robotics. Viser aims to bring easy and extensible 3D visualization to Python: we provide a comprehensive set of 3D scene and 2D GUI primitives, which can be used independently with minimal setup or composed to build specialized interfaces. This technical report describes Viser's features, interface, and implementation. Key design choices include an imperative-style API and a web-based viewer, which improve compatibility with modern programming patterns and workflows.

cs.CV↗

arXiv2025

Reconstructing People, Places, and Cameras

We present "Humans and Structure from Motion" (HSfM), a method for jointly reconstructing multiple human meshes, scene point clouds, and camera parameters in a metric world coordinate system from a sparse set of uncalibrated multi-view images featuring people. Our approach combines data-driven scene reconstruction with the traditional Structure-from-Motion (SfM) framework to achieve more accurate scene reconstruction and camera estimation, while simultaneously recovering human meshes. In contrast to existing scene reconstruction and SfM methods that lack metric scale information, our method estimates approximate metric scale by leveraging a human statistical model. Furthermore, it reconstructs multiple human meshes within the same world coordinate system alongside the scene point cloud, effectively capturing spatial relationships among individuals and their positions in the environment. We initialize the reconstruction of humans, scenes, and cameras using robust foundational models and jointly optimize these elements. This joint optimization synergistically improves the accuracy of each component. We compare our method to existing approaches on two challenging benchmarks, EgoHumans and EgoExo4D, demonstrating significant improvements in human localization accuracy within the world coordinate frame (reducing error from 3.51m to 1.04m in EgoHumans and from 2.9m to 0.56m in EgoExo4D). Notably, our results show that incorporating human data into the SfM pipeline improves camera pose estimation (e.g., increasing RRA@15 by 20.3% on EgoHumans). Additionally, qualitative results show that our approach improves overall scene reconstruction quality. Our code is available at: https://github.com/hongsukchoi/HSfM_RELEASE

cs.CV↗

arXiv2025

PyRoki: A Modular Toolkit for Robot Kinematic Optimization

Robot motion can have many goals. Depending on the task, we might optimize for pose error, speed, collision, or similarity to a human demonstration. Motivated by this, we present PyRoki: a modular, extensible, and cross-platform toolkit for solving kinematic optimization problems. PyRoki couples an interface for specifying kinematic variables and costs with an efficient nonlinear least squares optimizer. Unlike existing tools, it is also cross-platform: optimization runs natively on CPU, GPU, and TPU. In this paper, we present (i) the design and implementation of PyRoki, (ii) motion retargeting and planning case studies that highlight the advantages of PyRoki's modularity, and (iii) optimization benchmarking, where PyRoki can be 1.4-1.7x faster and converges to lower errors than cuRobo, an existing GPU-accelerated inverse kinematics library.

cs.RO↗

arXiv2025

Predict-Optimize-Distill: A Self-Improving Cycle for 4D Object Understanding

Humans can resort to long-form inspection to build intuition on predicting the 3D configurations of unseen objects. The more we observe the object motion, the better we get at predicting its 3D state immediately. Existing systems either optimize underlying representations from multi-view observations or train a feed-forward predictor from supervised datasets. We introduce Predict-Optimize-Distill (POD), a self-improving framework that interleaves prediction and optimization in a mutually reinforcing cycle to achieve better 4D object understanding with increasing observation time. Given a multi-view object scan and a long-form monocular video of human-object interaction, POD iteratively trains a neural network to predict local part poses from RGB frames, uses this predictor to initialize a global optimization which refines output poses through inverse rendering, then finally distills the results of optimization back into the model by generating synthetic self-labeled training data from novel viewpoints. Each iteration improves both the predictive model and the optimized motion trajectory, creating a virtuous cycle that bootstraps its own training data to learn about the pose configurations of an object. We also introduce a quasi-multiview mining strategy for reducing depth ambiguity by leveraging long video. We evaluate POD on 14 real-world and 5 synthetic objects with various joint types, including revolute and prismatic joints as well as multi-body configurations where parts detach or reattach independently. POD demonstrates significant improvement over a pure optimization baseline which gets stuck in local minima, particularly for longer videos. We also find that POD's performance improves with both video length and successive iterations of the self-improving cycle, highlighting its ability to scale performance with additional observations and looped refinement.

cs.CV↗

arXiv2025

St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World

Dynamic 3D reconstruction and point tracking in videos are typically treated as separate tasks, despite their deep connection. We propose St4RTrack, a feed-forward framework that simultaneously reconstructs and tracks dynamic video content in a world coordinate frame from RGB inputs. This is achieved by predicting two appropriately defined pointmaps for a pair of frames captured at different moments. Specifically, we predict both pointmaps at the same moment, in the same world, capturing both static and dynamic scene geometry while maintaining 3D correspondences. Chaining these predictions through the video sequence with respect to a reference frame naturally computes long-range correspondences, effectively combining 3D reconstruction with 3D tracking. Unlike prior methods that rely heavily on 4D ground truth supervision, we employ a novel adaptation scheme based on a reprojection loss. We establish a new extensive benchmark for world-frame reconstruction and tracking, demonstrating the effectiveness and efficiency of our unified, data-driven framework. Our code, model, and benchmark will be released.

cs.CV↗

arXiv2025

Segment Any Motion in Videos

Moving object segmentation is a crucial task for achieving a high-level understanding of visual scenes and has numerous downstream applications. Humans can effortlessly segment moving objects in videos. Previous work has largely relied on optical flow to provide motion cues; however, this approach often results in imperfect predictions due to challenges such as partial motion, complex deformations, motion blur and background distractions. We propose a novel approach for moving object segmentation that combines long-range trajectory motion cues with DINO-based semantic features and leverages SAM2 for pixel-level mask densification through an iterative prompting strategy. Our model employs Spatio-Temporal Trajectory Attention and Motion-Semantic Decoupled Embedding to prioritize motion while integrating semantic support. Extensive testing on diverse datasets demonstrates state-of-the-art performance, excelling in challenging scenarios and fine-grained segmentation of multiple objects. Our code is available at https://motion-seg.github.io/.

cs.CV↗

arXiv2025

Generating Continual Human Motion in Diverse 3D Scenes

We introduce a method to synthesize animator guided human motion across 3D scenes. Given a set of sparse (3 or 4) joint locations (such as the location of a person's hand and two feet) and a seed motion sequence in a 3D scene, our method generates a plausible motion sequence starting from the seed motion while satisfying the constraints imposed by the provided keypoints. We decompose the continual motion synthesis problem into walking along paths and transitioning in and out of the actions specified by the keypoints, which enables long generation of motions that satisfy scene constraints without explicitly incorporating scene information. Our method is trained only using scene agnostic mocap data. As a result, our approach is deployable across 3D scenes with various geometries. For achieving plausible continual motion synthesis without drift, our key contribution is to generate motion in a goal-centric canonical coordinate frame where the next immediate target is situated at the origin. Our model can generate long sequences of diverse actions such as grabbing, sitting and leaning chained together in arbitrary order, demonstrated on scenes of varying geometry: HPS, Replica, Matterport, ScanNet and scenes represented using NeRFs. Several experiments demonstrate that our method outperforms existing methods that navigate paths in 3D scenes. For more results we urge the reader to watch our supplementary video available at: https://www.youtube.com/watch?v=0wZgsdyCT4A&t=1s

cs.CV↗

arXiv2025

Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind

As humans move around, performing their daily tasks, they are able to recall where they have positioned objects in their environment, even if these objects are currently out of their sight. In this paper, we aim to mimic this spatial cognition ability. We thus formulate the task of Out of Sight, Not Out of Mind - 3D tracking active objects using observations captured through an egocentric camera. We introduce a simple but effective approach to address this challenging problem, called Lift, Match, and Keep (LMK). LMK lifts partial 2D observations to 3D world coordinates, matches them over time using visual appearance, 3D location and interactions to form object tracks, and keeps these object tracks even when they go out-of-view of the camera. We benchmark LMK on 100 long videos from EPIC-KITCHENS. Our results demonstrate that spatial cognition is critical for correctly locating objects over short and long time scales. E.g., for one long egocentric video, we estimate the 3D location of 50 active objects. After 120 seconds, 57% of the objects are correctly localised by LMK, compared to just 33% by a recent 3D method for egocentric videos and 17% by a general 2D tracking method.

cs.CV↗