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 11–20 of 124 papers

TitleStatusHype
Estimating Image Depth in the Comics DomainCode1
Unaligned Image-to-Image Translation by Learning to ReweightCode1
Independent Encoder for Deep Hierarchical Unsupervised Image-to-Image TranslationCode1
Underwater Image Restoration via Contrastive Learning and a Real-world DatasetCode1
Dual Contrastive Learning for Unsupervised Image-to-Image TranslationCode1
SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image TranslationCode1
Single Underwater Image Restoration by Contrastive LearningCode1
Spectral Synthesis for Satellite-to-Satellite TranslationCode1
Unsupervised Image-to-Image Translation via Pre-trained StyleGAN2 NetworkCode1
Unsupervised MRI Reconstruction with Generative Adversarial NetworksCode1
Show:102550
← PrevPage 2 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