46 citations · 125 across the 33 of their papers we have counts for
41 papers
UniGen-AR: Unifying Visual Generation with Auto-Regressive Modeling
Zhipeng Bao, Zhen Zhu, Nupur Kumari +4
Modern computer vision pipelines remain fragmented, with tasks such as text-to-image generation, editing, restoration, and classical perception handled by separate models. We study…
Robot Critics that Sweat the Small Stuff
Sruthi Sudhakar, Junbang Liang, Sreehari Rammohan +3
Large vision-language models contain several priors about the world and object interactions, making them useful critics during inference to steer robot policies towards success. Ho…
RoboDream: Compositional World Models for Scalable Robot Data Synthesis
Junjie Ye, Rong Xue, Basile Van Hoorick +6
Scaling robot learning requires large-scale, diverse demonstrations, yet real-world data collection via teleoperation remains prohibitively expensive and time-consuming. While vide…
Capturing Visual Environment Structure Correlates with Control Performance
Jiahua Dong, Yunze Man, Pavel Tokmakov +1
The choice of visual representation is key to scaling generalist robot policies. However, direct evaluation via policy rollouts is expensive, even in simulation. Existing proxy met…
AnyView: Synthesizing Any Novel View in Dynamic Scenes
Basile Van Hoorick, Dian Chen, Shun Iwase +7
Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world…
Walk through Paintings: Egocentric World Models from Internet Priors
Anurag Bagchi, Zhipeng Bao, Homanga Bharadhwaj +3
What if a video generation model could not only imagine a plausible future, but the correct one -- accurately reflecting how the world changes with each action? We answer this by p…
AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis
Junjie Ye, Rong Xue, Basile Van Hoorick +4
The collection of large-scale and diverse robot demonstrations remains a major bottleneck for imitation learning, as real-world data acquisition is costly and simulators offer limi…
Video Generators are Robot Policies
Junbang Liang, Pavel Tokmakov, Ruoshi Liu +4
Despite tremendous progress in dexterous manipulation, current visuomotor policies remain fundamentally limited by two challenges: they struggle to generalize under perceptual or b…
AllTracker: Efficient Dense Point Tracking at High Resolution
Adam W. Harley, Yang You, Xinglong Sun +11
We introduce AllTracker: a model that estimates long-range point tracks by way of estimating the flow field between a query frame and every other frame of a video. Unlike existing…
A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation
TRI LBM Team, Jose Barreiros, Andrew Beaulieu +79
Robot manipulation has seen tremendous progress in recent years, with imitation learning policies enabling successful performance of dexterous and hard-to-model tasks. Concurrently…
Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors
Wen-Hsuan Chu, Lei Ke, Jianmeng Liu +3
We tackle the challenge of generating dynamic 4D scenes from monocular, multi-object videos with heavy occlusions, and introduce GenMOJO, a novel approach that integrates rendering…
Understanding Complexity in VideoQA via Visual Program Generation
Cristobal Eyzaguirre, Igor Vasiljevic, Achal Dave +5
We propose a data-driven approach to analyzing query complexity in Video Question Answering (VideoQA). Previous efforts in benchmark design have relied on human expertise to design…
ReferEverything: Towards Segmenting Everything We Can Speak of in Videos
Anurag Bagchi, Zhipeng Bao, Yu-Xiong Wang +2
We present REM, a framework for segmenting a wide range of concepts in video that can be described through natural language. Our method leverages the universal visual-language mapp…
GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion
Vitor Guizilini, Pavel Tokmakov, Achal Dave +1
3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large la…
Dreamitate: Real-World Visuomotor Policy Learning via Video Generation
Junbang Liang, Ruoshi Liu, Ege Ozguroglu +5
A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments. A promising mechanism for learning robust policies is to leverage…
Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis
Basile Van Hoorick, Rundi Wu, Ege Ozguroglu +6
Accurate reconstruction of complex dynamic scenes from just a single viewpoint continues to be a challenging task in computer vision. Current dynamic novel view synthesis methods t…
pix2gestalt: Amodal Segmentation by Synthesizing Wholes
Ege Ozguroglu, Ruoshi Liu, Dídac Surís +4
We introduce pix2gestalt, a framework for zero-shot amodal segmentation, which learns to estimate the shape and appearance of whole objects that are only partially visible behind o…
Understanding Video Transformers via Universal Concept Discovery
Matthew Kowal, Achal Dave, Rares Ambrus +3
This paper studies the problem of concept-based interpretability of transformer representations for videos. Concretely, we seek to explain the decision-making process of video tran…
Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models
Wen-Hsuan Chu, Adam W. Harley, Pavel Tokmakov +3
Object tracking is central to robot perception and scene understanding. Tracking-by-detection has long been a dominant paradigm for object tracking of specific object categories. R…
Tracking through Containers and Occluders in the Wild
Basile Van Hoorick, Pavel Tokmakov, Simon Stent +2
Tracking objects with persistence in cluttered and dynamic environments remains a difficult challenge for computer vision systems. In this paper, we introduce , a ne…
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
Ziqi Pang, Jie Li, Pavel Tokmakov +3
This work proposes an end-to-end multi-camera 3D multi-object tracking (MOT) framework. It emphasizes spatio-temporal continuity and integrates both past and future reasoning for t…
Object Discovery from Motion-Guided Tokens
Zhipeng Bao, Pavel Tokmakov, Yu-Xiong Wang +2
Object discovery -- separating objects from the background without manual labels -- is a fundamental open challenge in computer vision. Previous methods struggle to go beyond clust…
Zero-1-to-3: Zero-shot One Image to 3D Object
Ruoshi Liu, Rundi Wu, Basile Van Hoorick +3
We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an object given just a single RGB image. To perform novel view synthesis in this under-constrained settin…
Breaking the "Object" in Video Object Segmentation
Pavel Tokmakov, Jie Li, Adrien Gaidon
The appearance of an object can be fleeting when it transforms. As eggs are broken or paper is torn, their color, shape and texture can change dramatically, preserving virtually no…