5 papers
Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment
Youming Deng, Songyou Peng, Junyi Zhang +5
Novel View Synthesis (NVS) has traditionally relied on models with explicit 3D inductive biases combined with known camera parameters from Structure-from-Motion (SfM) beforehand. R…
Visual Imitation Enables Contextual Humanoid Control
Arthur Allshire, Hongsuk Choi, Junyi Zhang +7
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…
St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
Haiwen Feng, Junyi Zhang, Qianqian Wang +5
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 s…
Pre-training Auto-regressive Robotic Models with 4D Representations
Dantong Niu, Yuvan Sharma, Haoru Xue +5
Foundation models pre-trained on massive unlabeled datasets have revolutionized natural language and computer vision, exhibiting remarkable generalization capabilities, thus highli…
DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo
Junzhe Zhu, Yuanchen Ju, Junyi Zhang +4
Dense 3D correspondence can enhance robotic manipulation by enabling the generalization of spatial, functional, and dynamic information from one object to an unseen counterpart. Co…