Browse State-of-the-Art › Image-to-Image Translation

Image-to-Image Translation

550 papers with code · 38 benchmarks · 32 datasets archive 2025-07-28

Computer Vision

Image-to-Image Translation is a task in computer vision and machine learning where the goal is to learn a mapping between an input image and an output image, such that the output image can be used to perform a specific task, such as style transfer, data augmentation, or image restoration.

( Image credit: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

38 leaderboard tables shown for this task, 38 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 38 until expanded.

Syntology 8 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): GTAV-to-Cityscapes Labels (1 judged, 0 placed), Cityscapes Labels-to-Photo (1 judged, 1 placed), Cityscapes-to-Foggy Cityscapes (1 judged, 0 placed), BCI (1 judged, 0 placed), AFHQ (1 judged, 0 placed), BRATS (3 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
SYNTHIA-to-Cityscapes (28 rows) HRDA + PiPa PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain... code — Compare
GTAV-to-Cityscapes Labels (22 rows) MIC MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation code — Compare
Cityscapes Labels-to-Photo (21 rows) DP-SIMS (ConvNext-L) Unlocking Pre-trained Image Backbones for Semantic Image Synthesis — — Compare
ADE20K Labels-to-Photos (16 rows) DP-SIMS (ConvNext-L) Unlocking Pre-trained Image Backbones for Semantic Image Synthesis — — Compare
COCO-Stuff Labels-to-Photos (15 rows) DP-SIMS (ConvNext-XL) Unlocking Pre-trained Image Backbones for Semantic Image Synthesis — — Compare
ADE20K-Outdoor Labels-to-Photos (7 rows) DP-GAN Dual Pyramid Generative Adversarial Networks for Semantic Image Synthesis code — Compare
IXI (7 rows) ResViT ResViT: Residual vision transformers for multi-modal medical image... code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
CelebA-HQ (6 rows) StarGAN v2 StarGAN v2: Diverse Image Synthesis for Multiple Domains code Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
Cityscapes-to-Foggy Cityscapes (6 rows) MIC MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation code — Compare
cat2dog (5 rows) GNR GANs N' Roses: Stable, Controllable, Diverse Image to Image... code — Compare
Cityscapes Photo-to-Labels (5 rows) pix2pix Image-to-Image Translation with Conditional Adversarial Networks code Syntology 74 ran (of which 0 constructed an object rather than computing a result; 66 with no instrument failure: 4 honoured, 5 violated, 57 with no contract checked; 8 where Syntology's instrument failed) · 48 unverified Compare
BCI (4 rows) pyramidpix2pix BCI: Breast Cancer Immunohistochemical Image Generation through... code — Compare
FLIR (4 rows) Pix2Next Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image... code — Compare
horse2zebra (4 rows) U-GAT-IT U-GAT-IT: Unsupervised Generative Attentional Networks with... code Syntology official (archive's flag): 4 ran · 24 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified Compare
LLVIP (4 rows) pyramidpix2pix BCI: Breast Cancer Immunohistochemical Image Generation through... code — Compare
RaFD (4 rows) StarGAN StarGAN: Unified Generative Adversarial Networks for Multi-Domain... code Syntology 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified Compare
selfie2anime (4 rows) GNR GANs N' Roses: Stable, Controllable, Diverse Image to Image... code — Compare
photo2vangogh (3 rows) U-GAT-IT U-GAT-IT: Unsupervised Generative Attentional Networks with... code Syntology official (archive's flag): 4 ran · 24 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified Compare
vangogh2photo (3 rows) U-GAT-IT U-GAT-IT: Unsupervised Generative Attentional Networks with... code Syntology official (archive's flag): 4 ran · 24 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified Compare
zebra2horse (3 rows) U-GAT-IT U-GAT-IT: Unsupervised Generative Attentional Networks with... code Syntology official (archive's flag): 4 ran · 24 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified Compare
Aerial-to-Map (2 rows) cGAN Image-to-Image Translation with Conditional Adversarial Networks code Syntology 74 ran (of which 0 constructed an object rather than computing a result; 66 with no instrument failure: 4 honoured, 5 violated, 57 with no contract checked; 8 where Syntology's instrument failed) · 48 unverified Compare
AFHQ (2 rows) StarGAN v2 StarGAN v2: Diverse Image Synthesis for Multiple Domains code Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified Compare
anime-to-selfie (2 rows) FQ-GAN Feature Quantization Improves GAN Training code Syntology official (archive's flag): 1 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
Deep-Fashion (2 rows) INADE Diverse Semantic Image Synthesis via Probability Distribution Modeling code Syntology official (archive's flag): 3 ran · 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result Compare
Object Transfiguration (sheep-to-giraffe) (2 rows) InstaGAN InstaGAN: Instance-aware Image-to-Image Translation code — Compare
selfie-to-anime (2 rows) FQ-GAN Feature Quantization Improves GAN Training code Syntology official (archive's flag): 1 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified Compare
SYNTHIA Fall-to-Winter (2 rows) CyCADA CyCADA: Cycle-Consistent Adversarial Domain Adaptation code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
2017_test set (1 row) hi (0,4) brane box models — — Compare
ADE-Indoor Labels-to-Photo (1 row) SB-GAN Semantic Bottleneck Scene Generation code — Compare
AFHQ (Cat to Dog) (1 row) EGSDE EGSDE: Unpaired Image-to-Image Translation via Energy-Guided... code — Compare
AFHQ (Wild to Dog) (1 row) EGSDE EGSDE: Unpaired Image-to-Image Translation via Energy-Guided... code — Compare
Apples and Oranges (1 row) Shared discriminator GAN Learning Unsupervised Cross-domain Image-to-Image Translation... code — Compare
BRATS (1 row) ResViT ResViT: Residual vision transformers for multi-modal medical image... code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified Compare
dog2cat (1 row) U-GAT-IT U-GAT-IT: Unsupervised Generative Attentional Networks with... code Syntology official (archive's flag): 4 ran · 24 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified Compare
KITTI Object Tracking Evaluation 2012 (1 row) SRNet Editing Text in the Wild code — Compare
photo2portrait (1 row) U-GAT-IT U-GAT-IT: Unsupervised Generative Attentional Networks with... code Syntology official (archive's flag): 4 ran · 24 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified Compare
portrait2photo (1 row) U-GAT-IT U-GAT-IT: Unsupervised Generative Attentional Networks with... code Syntology official (archive's flag): 4 ran · 24 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified Compare
Zebra and Horses (1 row) Shared discriminator GAN Learning Unsupervised Cross-domain Image-to-Image Translation... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

32 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 32 until expanded.

Subtasks archive 2025-07-28

11 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 1,184 · with a code link: 550 · where Syntology ran a sample: 126 (106 with a run with no instrument failure, 20 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (126 of 1,184 tagged: 106 with a run with no instrument failure, 20 where every run was a failure of Syntology's instrument)

Page 1 of 12: papers 1 to 100 of 1,184, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 58 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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