Papers › GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)

GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)

11 Jun 2021arXiv:2106.06561archive 2025-07-28

Min Jin Chong, David Forsyth

We show how to learn a map that takes a content code, derived from a face image, and a randomly chosen style code to an anime image. We derive an adversarial loss from our simple and effective definitions of style and content. This adversarial loss guarantees the map is diverse -- a very wide range of anime can be produced from a single content code. Under plausible assumptions, the map is not just diverse, but also correctly represents the probability of an anime, conditioned on an input face. In contrast, current multimodal generation procedures cannot capture the complex styles that appear in anime. Extensive quantitative experiments support the idea the map is correct. Extensive qualitative results show that the method can generate a much more diverse range of styles than SOTA comparisons. Finally, we show that our formalization of content and style allows us to perform video to video translation without ever training on videos.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mchong6/GANsNRoses officialmentioned in papermentioned on GitHubpytorch report
ZackPashkin/text2cartoon-pytorch-CLIP mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image-to-Image TranslationTranslationmultimodal generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-to-Image Translation cat2dog GNR DFID 26.1 #1 of 5 Archive leaderboard report
Image-to-Image Translation cat2dog GNR FID 26.9 #1 of 5 Archive leaderboard report
Image-to-Image Translation cat2dog StarGANv2 DFID 53.6 #2 of 5 Archive leaderboard report
Image-to-Image Translation cat2dog StarGANv2 FID 44.2 #2 of 5 Archive leaderboard report
Image-to-Image Translation cat2dog DRIT++ DFID 160.1 #3 of 5 Archive leaderboard report
Image-to-Image Translation cat2dog DRIT++ FID 91.5 #3 of 5 Archive leaderboard report
Image-to-Image Translation cat2dog CouncilGAN DFID 172.5 #4 of 5 Archive leaderboard report
Image-to-Image Translation cat2dog CouncilGAN FID 90.8 #4 of 5 Archive leaderboard report
Image-to-Image Translation selfie2anime GNR DFID 35.6 #1 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime GNR FID 34.4 #1 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime GNR LPIPS 0.505 #1 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime CouncilGAN DFID 56.2 #2 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime CouncilGAN FID 38.1 #2 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime CouncilGAN LPIPS 0.43 #2 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime StarGANv2 DFID 83.0 #3 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime StarGANv2 FID 59.8 #3 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime StarGANv2 LPIPS 0.427 #3 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime DRIT++ DFID 94.6 #4 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime DRIT++ FID 63.8 #4 of 4 Archive leaderboard report
Image-to-Image Translation selfie2anime DRIT++ LPIPS 0.201 #4 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections