English

Refining 3D Human Texture Estimation from a Single Image

Computer Vision and Pattern Recognition 2023-03-08 v1

Abstract

Estimating 3D human texture from a single image is essential in graphics and vision. It requires learning a mapping function from input images of humans with diverse poses into the parametric (UV) space and reasonably hallucinating invisible parts. To achieve a high-quality 3D human texture estimation, we propose a framework that adaptively samples the input by a deformable convolution where offsets are learned via a deep neural network. Additionally, we describe a novel cycle consistency loss that improves view generalization. We further propose to train our framework with an uncertainty-based pixel-level image reconstruction loss, which enhances color fidelity. We compare our method against the state-of-the-art approaches and show significant qualitative and quantitative improvements.

Keywords

Cite

@article{arxiv.2303.03471,
  title  = {Refining 3D Human Texture Estimation from a Single Image},
  author = {Said Fahri Altindis and Adil Meric and Yusuf Dalva and Ugur Gudukbay and Aysegul Dundar},
  journal= {arXiv preprint arXiv:2303.03471},
  year   = {2023}
}