Coherent Reconstruction of Multiple Humans From a Single Image

Wen Jiang, Nikos Kolotouros, Georgios Pavlakos, Xiaowei Zhou, Kostas Daniilidis
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Coherent reconstruction of pose and shape for multiple people. Typical top-down regression baselines (center) suffer from predicting people in overlapping positions, or in inconsistent depth orderings. Our approach (right) is trained to respect all these constraints and recover a coherent reconstruction of all the people in the scene in a feedforward manner.
doi:10.1109/cvpr42600.2020.00562 dblp:conf/cvpr/JiangKPZD20 fatcat:c5ayajgp6ndjtjwv5d3ox57sza