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/.

翻译：我们提出3DHumanGAN，一种三维感知生成对抗网络，能够合成具有一致外观的全方位人体逼真图像，并支持不同视角和身体姿态的变换。为解决合成人体关节结构时面临的表征与计算挑战，我们设计了一种新型生成器架构：通过3D姿态映射网络对2D卷积主干网络进行调制。该3D姿态映射网络被构建为一种可渲染的隐函数，其条件为带姿态的三维人体网格。该设计具备以下优势：i) 利用2D GAN的优势生成高质量图像；ii) 在不同视角和姿态下生成一致性图像；iii) 模型可融入三维人体先验信息并实现姿态条件控制。项目页面：https://3dhumangan.github.io/。