A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis

NeurIPS 2021

Xingang Pan1      Xudong Xu2      Chen Change Loy3      Christian Theobalt1      Bo Dai3


The advancement of generative radiance fields has pushed the boundary of 3D-aware image synthesis. Motivated by the observation that a 3D object should look realistic from multiple viewpoints, these methods introduce a multi-view constraint as regularization to learn valid 3D radiance fields from 2D images. Despite the progress, they often fall short of capturing accurate 3D shapes due to the shape-color ambiguity, limiting their applicability in downstream tasks. In this work, we address this ambiguity by proposing a novel shading-guided generative implicit model that is able to learn a starkly improved shape representation. Our key insight is that an accurate 3D shape should also yield a realistic rendering under different lighting conditions. This multi-lighting constraint is realized by modeling illumination explicitly and performing shading with various lighting conditions. Gradients are derived by feeding the synthesized images to a discriminator. To compensate for the additional computational burden of calculating surface normals, we further devise an efficient volume rendering strategy via surface tracking, reducing the training and inference time by 24% and 48%, respectively. Our experiments on multiple datasets show that the proposed approach achieves photorealistic 3D-aware image synthesis while capturing accurate underlying 3D shapes. We demonstrate improved performance of our approach on 3D shape reconstruction against existing methods, and show its applicability on image relighting. Our code is available at https://github.com/XingangPan/ShadeGAN.


Simultaneously change viewpoint, lighting, and identity.

Qualitative Results

Our approach synthesizes more accurate 3D shapes than pi-GAN and GRAF, and also learns to disentangle shading with albedo.




    title   = {A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis},
    author  = {Pan, Xingang and Xu, Xudong and Loy, Chen Change and Theobalt, Christian and Dai, Bo},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    year    = {2021}