3D human segmentation has seen noticeable progress in re-cent years. It, however, still remains a challenge to date. In this paper, weintroduce a deep patch-based method for 3D human segmentation. Wefirst extract a local surface patch for each vertex and then parameterizeit into a 2D grid (or image). We then embed identified shape descriptorsinto the 2D grids which are further fed into the powerful 2D Convolu-tional Neural Network for regressing corresponding semantic labels (e.g.,head, torso). Experiments demonstrate that our method is effective inhuman segmentation, and achieves state-of-the-art accuracy.
@article{arxiv.2007.05661,
title = {Deep Patch-based Human Segmentation},
author = {Dongbo Zhang and Zheng Fang and Xuequan Lu and Hong Qin and Antonio Robles-Kelly and Chao Zhang and Ying He},
journal= {arXiv preprint arXiv:2007.05661},
year = {2020}
}