Deep Patch-based Human Segmentation

TL;DR

This paper presents a deep patch-based approach for 3D human segmentation that converts local surface patches into 2D grids, enabling the use of CNNs for accurate semantic labeling, achieving state-of-the-art results.

Contribution

It introduces a novel patch-based method that transforms 3D surface patches into 2D representations for improved segmentation accuracy.

Findings

Achieves state-of-the-art accuracy in 3D human segmentation.

Effective use of 2D CNNs on surface patches.

Demonstrates robustness across different datasets.

Abstract

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.