Reversible GANs for Memory-efficient Image-to-Image Translation

Code

• github.com/tychovdo/RevGAN
  Officialpytorch★ 0
• github.com/silvandeleemput/memcnn
  pytorch★ 256
• github.com/ganslate-team/ganslate
  pytorch★ 38

Abstract

The Pix2pix and CycleGAN losses have vastly improved the qualitative and quantitative visual quality of results in image-to-image translation tasks. We extend this framework by exploring approximately invertible architectures which are well suited to these losses. These architectures are approximately invertible by design and thus partially satisfy cycle-consistency before training even begins. Furthermore, since invertible architectures have constant memory complexity in depth, these models can be built arbitrarily deep. We are able to demonstrate superior quantitative output on the Cityscapes and Maps datasets at near constant memory budget.

Tasks

Reproductions