-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Abdal_2023_CVPR, author = {Abdal, Rameen and Lee, Hsin-Ying and Zhu, Peihao and Chai, Menglei and Siarohin, Aliaksandr and Wonka, Peter and Tulyakov, Sergey}, title = {3DAvatarGAN: Bridging Domains for Personalized Editable Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {4552-4562} }
3DAvatarGAN: Bridging Domains for Personalized Editable Avatars
Abstract
Modern 3D-GANs synthesize geometry and texture by training on large-scale datasets with a consistent structure. Training such models on stylized, artistic data, with often unknown, highly variable geometry, and camera information has not yet been shown possible. Can we train a 3D GAN on such artistic data, while maintaining multi-view consistency and texture quality? To this end, we propose an adaptation framework, where the source domain is a pre-trained 3D-GAN, while the target domain is a 2D-GAN trained on artistic datasets. We, then, distill the knowledge from a 2D generator to the source 3D generator. To do that, we first propose an optimization-based method to align the distributions of camera parameters across domains. Second, we propose regularizations necessary to learn high-quality texture, while avoiding degenerate geometric solutions, such as flat shapes. Third, we show a deformation-based technique for modeling exaggerated geometry of artistic domains, enabling---as a byproduct---personalized geometric editing. Finally, we propose a novel inversion method for 3D-GANs linking the latent spaces of the source and the target domains. Our contributions---for the first time---allow for the generation, editing, and animation of personalized artistic 3D avatars on artistic datasets.
Related Material