DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras
We propose DeepMultiCap, a novel method for multi-person performance capture using sparse multi-view cameras. Our method can capture time varying surface details without the need of using pre-scanned template models. Given only sparse multi-view RGB videos (5~8), our method is able to reconstruct various kinds of 3D shapes with temporal-varying surface details even under challenging occlusions for multi-person interactive scenarios. or quantitative evaluation, we contribute a high quality multi-person dataset, MultiHuman, which consists of 150 static scenes with different levels of occlusions and ground truth 3D human models.
Yang Zheng, Ruizhi Shao, Yuxiang Zhang, Tao Yu, Zerong Zheng, Qionghai Dai and Yebin Liu. "DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras". IEEE ICCV 2021
http://www.liuyebin.com/dmc/dmc.html