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
ProPLIKS: Probablistic 3D human body pose estimation
Karthik Shetty, Annette Birkhold, Bernhard Egger, Srikrishna Jaganathan, Norbert Strobel, Markus Kowarschik, Andreas Maier
BodyMetric: Evaluating the Realism of HumanBodies in Text-to-Image Generation
Nefeli Andreou, Varsha Vivek, Ying Wang, Alex Vorobiov, Tiffany Deng, Raja Bala, Larry Davis, Betty Mohler Tesch
ShapeCraft: Body-Aware and Semantics-Aware 3D Object Design
Michelle Guo, Mia Tang, Hannah Cha, Ruohan Zhang, C. Karen Liu, Jiajun Wu
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