CycleGAN with Better Cycles

Tongzhou Wang, Yihan Lin
8/27/2024
cs.CVcs.LG

No confident code implementation found for this paper.

Abstract

CycleGAN provides a framework to train image-to-image translation with unpaired datasets using cycle consistency loss [4]. While results are great in many applications, the pixel level cycle consistency can potentially be problematic and causes unrealistic images in certain cases. In this project, we propose three simple modifications to cycle consistency, and show that such an approach achieves better results with fewer artifacts.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation

84% match1 repo962023

An Example for Domain Adaptation Using CycleGAN

80% match2026

UTSGAN: Unseen Transition Suss GAN for Transition-Aware Image-to-image Translation

79% match2023

Lost in Translation: Modern Neural Networks Still Struggle With Small Realistic Image Transformations

78% match2024

Unpaired Image-to-Image Translation using Adversarial Consistency Loss

78% match1 repo1502020

Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translation

78% match1 repo172023

Cite this paper

@article{wang2024cyclegan,
  title  = {CycleGAN with Better Cycles},
  author = {Tongzhou Wang and Yihan Lin},
  year   = {2024},
  eprint = {2408.15374},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.15374v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.15374.svg)](https://codeofpaper.com/paper/2408.15374)

Discussion