Loading ...
60%

3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping

ICCV 2023

Zhuoqian Yang1,2, Shikai Li1, Wayne Wu1† , Bo Dai1
1Shanghai AI Laboratory, 2EPFL
Note: Please use a browser other than Safari for HTML5 videos to play properly.

Abstract

We present 3DHumanGAN, a 3D-aware generative adversarial network that synthesizes photorealistic images of full-body humans with consistent appearances under different view-angles and body-poses. To tackle the representational and computational challenges in synthesizing the articulated structure of human bodies, we propose a novel generator architecture in which a 2D convolutional backbone is modulated by a 3D pose mapping network. The 3D pose mapping network is formulated as a renderable implicit function conditioned on a posed 3D human mesh. This design has several merits: i) it leverages the strength of 2D GANs to produce high-quality images; ii) it generates consistent images under varying view-angles and poses; iii) the model can incorporate the 3D human prior and enable pose conditioning.

Video Demo



Pose Interpolation

Our 3D-aware GAN can be used to render simple animation of generated humans by interpolating between poses.






BibTeX

If you find this work useful for your research, please consider citing our paper:

@inproceedings{yang20233dhumangan,
  title={3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping},
  author={Yang, Zhuoqian and Li, Shikai and Wu, Wayne and Dai, Bo},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={23008--23019},
  year={2023}
}