Pith

open record

sign in

arxiv: 2408.15374 · v2 · pith:JGUR5D2S · submitted 2024-08-27 · cs.CV · cs.LG

CycleGAN with Better Cycles

Tongzhou Wang , Yihan Lin This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:JGUR5D2Srecord.jsonopen to challenge →

classification cs.CV cs.LG
keywords consistencycyclebettercycleganresultsachievesapplicationsapproach
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. WarpI2I: Image Warping for Image-to-Image Translation

    cs.CV 2026-06 unverdicted novelty 6.0

    A saliency-guided warp-unwarp method reallocates spatial representation to preserve fine structures in latent diffusion models for image-to-image translation.

  2. DSA-CycleGAN: A Domain Shift Aware CycleGAN for Robust Multi-Stain Glomeruli Segmentation

    cs.CV 2026-04 unverdicted novelty 4.0

    DSA-CycleGAN reduces noise from CycleGAN stain transfers and improves glomeruli segmentation performance across multiple stains, especially biologically distinct ones.