Computer Vision Section 065

Image Generation and Restoration

The machinery inside image generators, and the closely related job of repairing photos that already exist.

11 of 11 lessons published Three reading levels on every lesson

Start with “Why GANs are hard to train”

Lessons in order

Work top to bottom. Each lesson assumes the one above it.

  1. Why GANs are hard to train
  2. StyleGAN and latent space
  3. Image-to-image translation
  4. The denoising U-Net
  5. Latent diffusion
  6. Classifier-free guidance
  7. Diffusion samplers and step counts
  8. ControlNet
  9. Inpainting and outpainting
  10. Super-resolution
  11. Watermarking and provenance