SOTAVerified

Unsupervised Image-To-Image Translation

Unsupervised image-to-image translation is the task of doing image-to-image translation without ground truth image-to-image pairings.

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 61–70 of 124 papers

TitleStatusHype
Image-to-image Mapping with Many Domains by Sparse Attribute Transfer—0
Rethinking the Truly Unsupervised Image-to-Image TranslationCode1
Breaking the Cycle - Colleagues Are All You NeedCode1
DUNIT: Detection-Based Unsupervised Image-to-Image TranslationCode1
Medical Image Generation using Generative Adversarial Networks—0
StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo MatchingCode1
TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired ImagesCode1
Structural-analogy from a Single Image PairCode1
Feature Quantization Improves GAN TrainingCode1
Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution AlignmentCode0
Show:102550
← PrevPage 7 of 13Next →
All datasetsSVNH-to-MNISTFreiburg Forest Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CyCADA pixel+featClassification Accuracy90.4—Unverified
2DTNClassification Accuracy84.4—Unverified
3ADDAClassification Accuracy76—Unverified
4DANNClassification Accuracy73.6—Unverified
#ModelMetricClaimedVerifiedStatus
1In2IPSNR21.65—Unverified
2cycGANPSNR18.57—Unverified
3UNITPSNR9.42—Unverified