CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis

19 Oct 2021  ·  Peng Zhou, Lingxi Xie, Bingbing Ni, Qi Tian ·

The style-based GAN (StyleGAN) architecture achieved state-of-the-art results for generating high-quality images, but it lacks explicit and precise control over camera poses. The recently proposed NeRF-based GANs made great progress towards 3D-aware generators, but they are unable to generate high-quality images yet... This paper presents CIPS-3D, a style-based, 3D-aware generator that is composed of a shallow NeRF network and a deep implicit neural representation (INR) network. The generator synthesizes each pixel value independently without any spatial convolution or upsampling operation. In addition, we diagnose the problem of mirror symmetry that implies a suboptimal solution and solve it by introducing an auxiliary discriminator. Trained on raw, single-view images, CIPS-3D sets new records for 3D-aware image synthesis with an impressive FID of 6.97 for images at the $256\times256$ resolution on FFHQ. We also demonstrate several interesting directions for CIPS-3D such as transfer learning and 3D-aware face stylization. The synthesis results are best viewed as videos, so we recommend the readers to check our github project at https://github.com/PeterouZh/CIPS-3D read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
3D-Aware Image Synthesis FFHQ 256 x 256 pi-GAN FID 34.56 # 3
KID 26.58 # 3
3D-Aware Image Synthesis FFHQ 256 x 256 StyleNeRF FID 8.00 # 2
KID 3.70 # 2
3D-Aware Image Synthesis FFHQ 256 x 256 GIRAFFE FID 63.33 # 4
KID 50.94 # 4
3D-Aware Image Synthesis FFHQ 256 x 256 CIPS-3D FID 6.97 # 1
KID 2.87 # 1

Methods