Browse SoTA > Computer Vision > Image-to-Image Translation > Unsupervised Image-To-Image Translation

Unsupervised Image-To-Image Translation

36 papers with code · Computer Vision

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 )

Benchmarks

Latest papers with code

The Surprising Effectiveness of Linear Unsupervised Image-to-Image Translation

24 Jul 2020eitanrich/lin-im2im

Unsupervised image-to-image translation is an inherently ill-posed problem.

UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

23
24 Jul 2020

Rethinking the Truly Unsupervised Image-to-Image Translation

11 Jun 2020clovaai/tunit

In this paper, we tackle image-to-image translation in a fully unsupervised setting, i. e., neither paired images nor domain labels.

UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

265
11 Jun 2020

Breaking the Cycle - Colleagues Are All You Need

CVPR 2020 Onr/Council-GAN

(2) Since it does not need to support the cycle constraint, no irrelevant traces of the input are left on the generated image.

MULTIMODAL UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

83
01 Jun 2020

TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images

9 Apr 2020linjx-ustc1106/TuiGAN-PyTorch

With TuiGAN, an image is translated in a coarse-to-fine manner where the generated image is gradually refined from global structures to local details.

UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

101
09 Apr 2020

Feature Quantization Improves GAN Training

5 Apr 2020YangNaruto/FQ-GAN

The instability in GAN training has been a long-standing problem despite remarkable research efforts.

CONDITIONAL IMAGE GENERATION FACE GENERATION QUANTIZATION UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

96
05 Apr 2020

Structural-analogy from a Single Image Pair

5 Apr 2020rmokady/structural-analogy

In this paper, we explore the capabilities of neural networks to understand image structure given only a single pair of images, A and B.

UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

80
05 Apr 2020

Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation

CVPR 2020 alpc91/NICE-GAN-pytorch

The proposed architecture, termed as NICE-GAN, exhibits two advantageous patterns over previous approaches: First, it is more compact since no independent encoding component is required; Second, this plug-in encoder is directly trained by the adversary loss, making it more informative and trained more effectively if a multi-scale discriminator is applied.

UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

87
29 Feb 2020

GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation

24 Feb 2020wallacemplira/ganhopper

Instead of executing translation directly, we steer the translation by requiring the network to produce in-between images that resemble weighted hybrids between images from the input domains.

UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

4
24 Feb 2020

Adversarial Self-Defense for Cycle-Consistent GANs

NeurIPS 2019 dbash/pix2pix_cyclegan_guess_noise

The goal of unsupervised image-to-image translation is to map images from one domain to another without the ground truth correspondence between the two domains.

ADVERSARIAL ATTACK UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION

8
01 Dec 2019