3D Human Body
3D human body modeling research focuses on accurately and efficiently reconstructing three-dimensional human representations from various input modalities, including single images, multi-view videos, LiDAR scans, and RGB-D data. Current efforts concentrate on improving robustness to occlusions and challenging conditions (e.g., poor lighting, loose clothing), leveraging advanced architectures like transformers and diffusion models, and exploring efficient methods for handling high-resolution data. This field is crucial for numerous applications, ranging from virtual reality and healthcare to animation and human-computer interaction, driving advancements in computer vision, machine learning, and related disciplines.
Papers
LiDAR-HMR: 3D Human Mesh Recovery from LiDAR
Bohao Fan, Wenzhao Zheng, Jianjiang Feng, Jie Zhou
Enhanced Spatio-Temporal Context for Temporally Consistent Robust 3D Human Motion Recovery from Monocular Videos
Sushovan Chanda, Amogh Tiwari, Lokender Tiwari, Brojeshwar Bhowmick, Avinash Sharma, Hrishav Barua