Human Motion Transfer with 3D Constraints and Detail Enhancement
Lists
Only you see this
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.
BibTeX
@article{sun2020human,
author = {Yang-Tian Sun and Qian-Cheng Fu and Yue-Ren Jiang and Zitao Liu and Yu-Kun Lai and Hongbo Fu and Lin Gao},
title = {{Human Motion Transfer with 3D Constraints and Detail Enhancement}},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
year = {2020},
doi = {10.1109/tpami.2022.3201904},
}| Copy Motion From One to Another: Fake Motion Video Generation | IJCAI · 2022 |
| Everybody Dance Now | arXiv · 2018 |
| Human Action Transfer Based on 3D Model Reconstruction | AAAI · 2019 |
| Synthesizing Moving People with 3D Control | arXiv · 2024 |
| Dance Dance Generation: Motion Transfer for Internet Videos | Workshops @ ICCV · 2019 |
| REMOT: A Region-to-Whole Framework for Realistic Human Motion Transfer | arXiv · 2022 |