High-Fidelity Clothed Avatar Reconstruction from a Single Image
Code Paper Homepage Youtube
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.
| Author(s): | Liao, Tingting and Zhang, Xiaomei and Xiu, Yuliang and Yi, Hongwei and Liu, Xudong and Qi, Guo-Jun and Zhang, Yong and Wang, Xuan and Zhu, Xiangyu and Lei, Zhen |
| Links: | |
| Book Title: | IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR) |
| Pages: | 8662--8672 |
| Year: | 2023 |
| Month: | June |
| BibTeX Type: | Conference Paper (inproceedings) |
| Event Name: | CVPR 2023 |
| Event Place: | Vancouver, Canada |
| State: | Published |
| URL: | https://tingtingliao.github.io/CAR/ |
| Electronic Archiving: | grant_archive |
BibTeX
@inproceedings{car2023liao,
title = {High-Fidelity Clothed Avatar Reconstruction from a Single Image},
booktitle = {IEEE/CVF Conf.~on Computer Vision and Pattern Recognition (CVPR)},
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. },
pages = {8662--8672},
month = jun,
year = {2023},
author = {Liao, Tingting and Zhang, Xiaomei and Xiu, Yuliang and Yi, Hongwei and Liu, Xudong and Qi, Guo-Jun and Zhang, Yong and Wang, Xuan and Zhu, Xiangyu and Lei, Zhen},
url = {https://tingtingliao.github.io/CAR/},
month_numeric = {6}
}