Deep Patch-based Human Segmentation

2020/07/11 by Dongbo Zhang, Zheng Fang, Zhang, Dongbo +11
Computer Science · Engineering · #3D Shape Modeling and Analysis #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Graphics (cs.GR) #Human Pose and Action Recognition #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.2007.05661

openalex publication_date 2020/07/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fast exact and approximate geodesics on meshes
• MeshCNN

Related

• Part Segmentation of Human Meshes via Multi-View Human Parsing
• Deep Neural Patchworks: Coping with Large Segmentation Tasks
• A Deep Neural Network Tool for Automatic Segmentation of Human Body Parts in Natural Scenes
• DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image
• HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation