Paper-Stylegan-Image2StylegGAN
Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?Accept: 2019ICCV
Problem：基于优化(optimized-based)的StyleGAN反转
Framework提出w+空间。即优化的latent code由原先stylegan的w变为w+(原先stylegan的w空间是通过复制然后送入sty ...
Paper-StyleGAN-V1
A Style-Based Generator Architecture for Generative Adversarial NetworksAccept:CVPR2019code：github上一搜一大把(官方非官方，tf或者pytorch)
Problem:生成更加真实多样且高清的图像
Framework
上图(a)为ProgressiveGAN(Progressive growing o ...
GAN Prior Embedded Network for Blind Face Restoration in the Wild
Paper:GAN Prior Embedded Network for Blind Face Restoration in the WildAccept:CVPR2021Code
Problem:野外人脸复原(Blind face restoration)，属于人脸复原任务中的一种，类似于超分，inpainting等工作。文章为了解决野外人脸的退化复杂性(噪声，缺损，分辨率低等)，提出了解决方法 ...