文件名称：分析提高图像质量计算机视觉Analyzing and Improving the Image Quality of StyleGAN
文件大小：17.77MB
文件格式：PDF
更新时间：2023-04-01 11:22:22
深度学习 机器学习 人工智能 计算机视觉 GAN
Abstract The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent vectors to images. In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably detect if an image is generated by a particular network. We furthermore visualize how well the generator utilizes its output resolution, and identify a capacity problem, motivating us to train larger models for additional quality improvements. Overall, our improved model rede- fines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.