Skip to content

Instantly share code, notes, and snippets.

View phillipi's full-sized avatar

Phillip Isola phillipi

1.2k followers · 4 following
View GitHub Profile
@brannondorsey
brannondorsey / pix2pix_paper_notes.md
Last active January 3, 2022 09:57
Notes on the Pix2Pix (pixel-level image-to-image translation) Arxiv paper

Image-to-Image Translation with Conditional Adversarial Networks

Notes from arXiv:1611.07004v1 [cs.CV] 21 Nov 2016

  • Euclidean distance between predicted and ground truth pixels is not a good method of judging similarity because it yields blurry images.
  • GANs learn a loss function rather than using an existing one.
  • GANs learn a loss that tries to classify if the output image is real or fake, while simultaneously training a generative model to minimize this loss.
  • Conditional GANs (cGANs) learn a mapping from observed image x and random noise vector z to y: y = f(x, z)
  • The generator G is trained to produce outputs that cannot be distinguished from "real" images by an adversarially trained discrimintor, D which is trained to do as well as possible at detecting the generator's "fakes".
  • The discriminator D, learns to classify between real and synthesized pairs. The generator learns to fool the discriminator.
  • Unlike an unconditional GAN, both th