7 papers
C2Dex: Contact-Consistent Reconstruction and Retargeting for Dexterous Manipulation from Monocular Video
Jie Ren, Zhehao Jiang, Yinhong Yang +9
High-quality demonstrations for dexterous robot manipulation are costly and difficult to collect, whereas monocular human videos provide a scalable source of diverse manipulation b…
UNICA: A Unified Neural Framework for Controllable 3D Avatars
Jiahe Zhu, Xinyao Wang, Yiyu Zhuang +4
Controllable 3D human avatars have found widespread applications in 3D games, the metaverse, and AR/VR scenarios. The conventional approach to creating such a 3D avatar requires a…
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
Jiahao Wang, Yufeng Yuan, Rujie Zheng +12
Significant progress has been made in spatial intelligence, spanning both spatial reconstruction and world exploration. However, the scalability and real-world fidelity of current…
LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging
Zhijian Shu, Cheng Lin, Tao Xie +8
3D vision foundation models like Visual Geometry Grounded Transformer (VGGT) have advanced greatly in geometric perception. However, it is time-consuming and memory-intensive for l…
TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond
Yifei Zeng, Yajie Bao, Jiachen Qian +7
Prevailing 3D texture generation methods, which often rely on multi-view fusion, are frequently hindered by inter-view inconsistencies and incomplete coverage of complex surfaces,…
Pressure2Motion: Hierarchical Human Motion Reconstruction from Ground Pressure with Text Guidance
Zhengxuan Li, Qinhui Yang, Yiyu Zhuang +7
We present Pressure2Motion, a novel motion capture algorithm that reconstructs human motion from a ground pressure sequence and text prompt. At inference time, Pressure2Motion requ…