Our Research
PontTuset

BoPR: Body-aware Part Regressor for Human Shape and Pose Estimation
Yongkang Cheng, Shaoli Huang, Jineng Ning, Ying Shan,
arXiv preprint., 2023
arXiv / Project Page / Code

This paper presents a novel approach for estimating human body shape and pose from monocular images that effectively addresses the challenges of occlusions and depth ambiguity.

PontTuset

HMC: Hierarchical Mesh Coarsening for Skeleton-free Motion Retargeting
Haoyu Wang, Shaoli Huang, Fang Zhao, Chun Yuan, Ying Shan,
arXiv preprint., 2023
arXiv / Project Page / Code

HMC shows a simple yet effective way of better handling local-part motions in the skeleton-free motion retaregting task, and it also fixes many failure cases in previous literature regarding small-part motions and local-motion interdependencies.

PontTuset

ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
Zhengdi Yu, Shaoli Huang*, Chen Fang, Toby P. Breckon, Jue Wang
Conference on Computer Vision and Pattern Recognition (CVPR) , 2023
arXiv / Project Page / Code

We introduce the first one-stage arbitrary hand reconstruction method using only a monocular RGB image as input.

PontTuset

Learning Anchor Transformations for 3D Garment Animation
Fang Zhao, Zekun Li, Shaoli Huang*, Junwu Weng, Tianfei Zhou, Guo-Sen Xie, Jue Wang, Ying Shan
Conference on Computer Vision and Pattern Recognition (CVPR) , 2023
arXiv / Project Page / Code

This paper proposes an anchor-based deformation model, namely AnchorDEF, to predict 3D garment animation from a body motion sequence.

PontTuset

Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry
Jiaxu Zhang, Junwu Weng, Di Kang, Fang Zhao, Shaoli Huang, Xuefei Zhe, Linchao Bao, Ying Shan, Jue Wang, Zhigang Tu*
Conference on Computer Vision and Pattern Recognition (CVPR) , 2023
arXiv / Project Page / Code

R2ET is a neural motion retargeting model that can preserve source motion semantics and avoid interpenetration in target motion.


Last update: 2023.03.20