3DHumanGAN: 3D-Aware Human Image Generation with 3D Pose Mapping
This work addresses the challenge of 3D-aware human image generation for applications in computer vision and graphics, representing an incremental improvement by combining existing techniques.
The paper tackled the problem of generating photorealistic images of full-body humans with consistent appearances across different view-angles and body-poses, resulting in a model that synthesizes high-quality images by leveraging 2D GANs and 3D pose mapping.
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. Project page: https://3dhumangan.github.io/.