Deep Patch-based Human Segmentation
This addresses the challenge of 3D human segmentation for computer vision applications, but it is incremental as it builds on existing patch-based and CNN approaches.
The paper tackles 3D human segmentation by introducing a deep patch-based method that converts local surface patches into 2D grids for processing with a 2D CNN, achieving state-of-the-art accuracy.
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.