Deep Patch-Based Human Segmentation

3D human segmentation has seen noticeable progress in recent years. It, however, still remains a challenge to date. In this paper, we introduce a deep patch-based method for 3D human segmentation. We first extract a local surface patch for each vertex and then parameterize it into a 2D grid (or image). We then embed identified shape descriptors into the 2D grids which are further fed into the powerful 2D Convolutional Neural Network for regressing corresponding semantic labels (e.g., head, torso). Experiments demonstrate that our method is effective in human segmentation, and achieves state-of-the-art accuracy.