Human motion transfer with 3D constraints and detail enhancement

Sun, Yang-Tian, Fu, Qian-Cheng, Jiang, Yue-Ren, Liu, Zitao, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680, Fu, Hongbo and Gao, Lin 2022. Human motion transfer with 3D constraints and detail enhancement. IEEE Transactions on Pattern Analysis and Machine Intelligence 10.1109/TPAMI.2022.3201904

Preview

PDF - Accepted Post-Print Version Download (11MB) | Preview

Abstract

We propose a new method for realistic human motion transfer using a generative adversarial network (GAN), which generates a motion video of a target character imitating actions of a source character, while maintaining high authenticity of the generated results. We tackle the problem by decoupling and recombining the posture information and appearance information of both the source and target characters. The innovation of our approach lies in the use of the projection of a reconstructed 3D human model as the condition of GAN to better maintain the structural integrity of transfer results in different poses. We further introduce a detail enhancement net to enhance the details of transfer results by exploiting the details in real source frames. Extensive experiments show that our approach yields better results both qualitatively and quantitatively than the state-of-the-art methods.

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	0162-8828
Funders:	The Royal Society
Date of First Compliant Deposit:	1 September 2022
Date of Acceptance:	9 August 2022
Last Modified:	07 Nov 2023 10:47
URI:	https://orca.cardiff.ac.uk/id/eprint/152275

Actions (repository staff only)

Edit Item