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 31–40 of 124 papers

TitleStatusHype
Federated Contrastive Learning for Privacy-Preserving Unpaired Image-to-Image Translation—0
Unaligned Image-to-Image Translation by Learning to ReweightCode1
Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translationCode0
Independent Encoder for Deep Hierarchical Unsupervised Image-to-Image TranslationCode1
Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint—0
Underwater Image Restoration via Contrastive Learning and a Real-world DatasetCode1
Federated CycleGAN for Privacy-Preserving Image-to-Image Translation—0
Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation—0
Few-Shot Unsupervised Image-to-Image Translation on complex scenes—0
Contrastive Learning for Unsupervised Image-to-Image Translation—0
Show:102550
← PrevPage 4 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