English

PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction

Computer Vision and Pattern Recognition 2020-11-03 v2

Abstract

We introduce PeeledHuman - a novel shape representation of the human body that is robust to self-occlusions. PeeledHuman encodes the human body as a set of Peeled Depth and RGB maps in 2D, obtained by performing ray-tracing on the 3D body model and extending each ray beyond its first intersection. This formulation allows us to handle self-occlusions efficiently compared to other representations. Given a monocular RGB image, we learn these Peeled maps in an end-to-end generative adversarial fashion using our novel framework - PeelGAN. We train PeelGAN using a 3D Chamfer loss and other 2D losses to generate multiple depth values per-pixel and a corresponding RGB field per-vertex in a dual-branch setup. In our simple non-parametric solution, the generated Peeled Depth maps are back-projected to 3D space to obtain a complete textured 3D shape. The corresponding RGB maps provide vertex-level texture details. We compare our method with current parametric and non-parametric methods in 3D reconstruction and find that we achieve state-of-the-art-results. We demonstrate the effectiveness of our representation on publicly available BUFF and MonoPerfCap datasets as well as loose clothing data collected by our calibrated multi-Kinect setup.

Keywords

Cite

@article{arxiv.2002.06664,
  title  = {PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction},
  author = {Sai Sagar Jinka and Rohan Chacko and Avinash Sharma and P. J. Narayanan},
  journal= {arXiv preprint arXiv:2002.06664},
  year   = {2020}
}
R2 v1 2026-06-23T13:43:17.780Z