
PoP (Power of Points) is a point-based model for generating high-fidelity dense point clouds of humans in clothing with pose-dependent geometry. It supports modeling multiple subjects of varied body shapes and different outfit types with a single model. At test-time, given a single, static scan, the model can animate it with plausible pose-dependent deformations.
PoP (Power of Points) is a point-based model for generating high-fidelity dense point clouds of humans in clothing with pose-dependent geometry. It supports modeling multiple subjects of varied body shapes and different outfit types with a single model. At test-time, given a single, static scan, the model can animate it with plausible pose-dependent deformations.
Release Date: | 12 October 2021 |
licence_type: | PS:License 1.0 |
Authors: | Qianli Ma, Jinlong Yang, Siyu Tang, Michael J. Black |
Link (URL): | https://qianlim.github.io/POP |
Repository: | https://github.com/qianlim/POP |
Project(s): |