11 papers
UniLAP: A Unified Latent Action Policy for Cross-Embodiment Manipulation
Lei Yao, Qiao Feng, Mutian Tong +3
Latent Action Models (LAMs) can capture manipulation priors from action-free videos, but discrete latents usually impose a granularity bottleneck, limiting their ability to represe…
Scene and Human in One World: Reconstruction in a Feedforward Pass
Boao Shi, Qiao Feng, Yiming Huang +1
Reconstructing humans in dynamic scenes from moving monocular cameras remains challenging due to scale ambiguity, human-scene misalignment, and occlusion interference. Rather than…
UniPixie: Unified and Probabilistic 3D Physics Learning via Flow Matching
Qilin Huang, Quynh Anh Huynh, Long Le +5
Existing feed-forward networks excel at predicting a single set of physical properties from visual appearance, but this point-estimate paradigm fundamentally fails to capture the r…
PointAction: 3D Points as Universal Action Representations for Robot Control
Mutian Tong, Han Jiang, Qiao Feng +2
Video-Action Models (VAMs) leverage the broad visual dynamics captured by pre-trained video diffusion models, offering a promising path toward generalizable robot manipulation. How…
OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies
Yunzhou Song, Long Le, Yong-Hyun Park +7
Vision-language-action(VLA) models have shown great promise as generalist policies for a large range of relatively simple tasks. However, they demonstrate limited performance on mo…
Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation
Qingxuan Wu, Zhiyang Dou, Chuan Guo +5
Modeling human-human interactions from text remains challenging because it requires not only realistic individual dynamics but also precise, text-consistent spatiotemporal coupling…
PhysHMR: Learning Humanoid Control Policies from Vision for Physically Plausible Human Motion Reconstruction
Qiao Feng, Yiming Huang, Yufu Wang +2
Reconstructing physically plausible human motion from monocular videos remains a challenging problem in computer vision and graphics. Existing methods primarily focus on kinematics…
PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
Chen Wang, Chuhao Chen, Yiming Huang +4
Existing video generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability. To overcome these limit…
Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels
Long Le, Ryan Lucas, Chen Wang +4
Inferring the physical properties of 3D scenes from visual information is a critical yet challenging task for creating interactive and realistic virtual worlds. While humans intuit…
Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation
Chuhao Chen, Zhiyang Dou, Chen Wang +5
Faithfully reconstructing textured shapes and physical properties from videos presents an intriguing yet challenging problem. Significant efforts have been dedicated to advancing s…
ProTracker: Probabilistic Integration for Robust and Accurate Point Tracking
Tingyang Zhang, Chen Wang, Zhiyang Dou +4
We propose ProTracker, a novel framework for accurate and robust long-term dense tracking of arbitrary points in videos. Previous methods relying on global cost volumes effectively…