21 papers
Lifting Unlabeled Internet-level Data for 3D Scene Understanding
Yixin Chen, Yaowei Zhang, Huangyue Yu +9
Annotated 3D scene data is scarce and expensive to acquire, while abundant unlabeled videos are readily available on the internet. In this paper, we demonstrate that carefully desi…
LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning
Jiangyong Huang, Xiaojian Ma, Xiongkun Linghu +6
Developing vision-language models (VLMs) capable of understanding 3D scenes has been a longstanding research goal. Despite recent progress, 3D VLMs still struggle with spatial reas…
SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes
Xiongkun Linghu, Jiangyong Huang, Ziyu Zhu +2
Existing research on 3D Large Language Models (LLMs) still struggles to achieve grounded question-answering, primarily due to the under-exploration of the mechanism of human-like s…
OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control
Yunshen Wang, Shaohang Zhu, Peiyuan Zhi +7
High-fidelity motion tracking serves as the ultimate litmus test for generalizable, human-level motor skills. However, current policies often hit a "generality barrier": as motion…
OmniTrack: General Motion Tracking via Physics-Consistent Reference
Yuhan Li, Peiyuan Zhi, Yunshen Wang +6
Learning motion tracking from rich human motion data is a foundational task for achieving general control in humanoid robots, enabling them to perform diverse behaviors. However, d…
SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent
Yandan Yang, Baoxiong Jia, Shujie Zhang +1
Indoor scene synthesis has become increasingly important with the rise of Embodied AI, which requires 3D environments that are not only visually realistic but also physically plaus…