High-fidelity human avatars from a single RGB camera

Zhao, Hao, Zhang, Jinsong, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680, Zheng, Zerong, Xie, Yingdi, Liu, Yebin and Li, Kun 2022. High-fidelity human avatars from a single RGB camera. Presented at: 2022 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022), New Orleans, LA, USA, 19-24 June 2022. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE: 10.1109/CVPR52688.2022.01544

Preview

PDF - Accepted Post-Print Version Download (5MB) | Preview

Abstract

In this paper, we propose a coarse-to-fine framework to reconstruct a personalized high-fidelity human avatar from a monocular video. To deal with the misalignment problem caused by the changed poses and shapes in different frames, we design a dynamic surface network to recover pose-dependent surface deformations, which help to decouple the shape and texture of the person. To cope with the complexity of textures and generate photo-realistic results, we propose a reference-based neural rendering network and exploit a bottom-up sharpening-guided fine-tuning strategy to obtain detailed textures. Our frame-work also enables photo-realistic novel view/pose syn-thesis and shape editing applications. Experimental re-sults on both the public dataset and our collected dataset demonstrate that our method outperforms the state-of-the-art methods. The code and dataset will be available at http://cic.tju.edu.cn/faculty/likun/projects/HF-Avatar.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	In Press
Schools:	Computer Science & Informatics
ISBN:	9781665469470
Date of First Compliant Deposit:	2 April 2022
Date of Acceptance:	2 March 2022
Last Modified:	30 Nov 2022 13:24
URI:	https://orca.cardiff.ac.uk/id/eprint/149028

Actions (repository staff only)

Edit Item