Over the years, 2D GANs have achieved great successes in photorealistic portrait generation. However, they lack 3D understanding in the generation process, thus they suffer from multi-view inconsistency problem. To alleviate the issue, many 3D-aware GANs have been proposed and shown notable results, but 3D GANs struggle with editing semantic attributes. The controllability and interpretability of 3D GANs have not been much explored. In this work, we propose two solutions to overcome these weaknesses of 2D GANs and 3D-aware GANs. We first introduce a novel 3D-aware GAN, SURF-GAN, which is capable of discovering semantic attributes during training and controlling them in an unsupervised manner. After that, we inject the prior of SURF-GAN into StyleGAN to obtain a high-fidelity 3D-controllable generator. Unlike existing latent-based methods allowing implicit pose control, the proposed 3D-controllable StyleGAN enables explicit pose control over portrait generation. This distillation allows direct compatibility between 3D control and many StyleGAN-based techniques (e.g., inversion and stylization), and also brings an advantage in terms of computational resources. Our codes are available at https://github.com/jgkwak95/SURF-GAN.
翻译:多年来, 2D GANs 在光现实肖像制作中取得了巨大成功, 然而, 2D GANs 却在相片现实化肖像制作中取得了巨大成功, 但是, 2D GANs 的可控性和可解释性在相片肖像制作中取得了巨大成功, 然而, 他们缺乏对3D 的认知, 因而在生成过程中遭遇了多种观点不一致的问题。 为了缓解这一问题, 已经提出了许多 3D 维GANs 3D 的3D 级GANs, 并展示了显著的成果。 但是, 3D GANs 的可控性和可解释性并没有被广泛探讨。 在这项工作中, 我们首先引入了一个新的 3D-aware GAN, SURF-GAN 能够在培训中发现语义属性,并以不受监督的方式控制这些属性。 之后, 我们把 SYRF- GAN 以前的3D- D 可控性发电机, 不同于现有的允许隐含容容容的潜控法方法, 3D- 可控SylGAN GAN 能够对肖像生成进行明确的控制。 这种在3D- grancal- grantal- 和多种技术中可以直接兼容性。