High-Fidelity Clothed Avatar Reconstruction From a Single Image
Tingting Liao, Xiaomei Zhang, Yuliang Xiu, Hongwei Yi, Xudong Liu, Guo-Jun Qi, Yong Zhang, Xuan Wang
Abstract
This paper presents a framework for efficient 3D clothed avatar reconstruction. By combining the advantages of the high accuracy of optimization-based methods and the efficiency of learning-based methods, we propose a coarse-to-fine way to realize a high-fidelity clothed avatar reconstruction (CAR) from a single image. At the first stage, we use an implicit model to learn the general shape in the canonical space of a person in a learning-based way, and at the second stage, we refine the surface detail by estimating the non-rigid deformation in the posed space in an optimization way. A hyper-network is utilized to generate a good initialization so that the convergence of the optimization process is greatly accelerated. Extensive experiments on various datasets show that the proposed CAR successfully produces high-fidelity avatars for arbitrarily clothed humans in real scenes. The codes will be released.
BibTeX
@inproceedings{cvpr2023_highfidelityclot,
title = {High-Fidelity Clothed Avatar Reconstruction From a Single Image},
author = {Tingting Liao and Xiaomei Zhang and Yuliang Xiu and Hongwei Yi and Xudong Liu and Guo-Jun Qi and Yong Zhang and Xuan Wang and Xiangyu Zhu and Zhen Lei},
booktitle = {CVPR 2023},
year = {2023}
}