Multimodal Unsupervised Image-To-Image Translation
14 papers with code • 6 benchmarks • 4 datasets
Multimodal unsupervised image-to-image translation is the task of producing multiple translations to one domain from a single image in another domain.
( Image credit: MUNIT: Multimodal UNsupervised Image-to-image Translation )
Benchmarks
These leaderboards are used to track progress in Multimodal Unsupervised Image-To-Image Translation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Multimodal Unsupervised Image-To-Image Translation models and implementations
CelebA-HQ
AFHQ
CATS
FFHQ-Aging
Most implemented papers
Breaking the Cycle - Colleagues Are All You Need
(2) Since it does not need to support the cycle constraint, no irrelevant traces of the input are left on the generated image.
Image-to-image Translation via Hierarchical Style Disentanglement
imlixinyang/HiSD
•
•
CVPR 2021
Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation with diverse styles) tasks.
A Style-aware Discriminator for Controllable Image Translation
kunheek/style-aware-discriminator
•
•
CVPR 2022
Current image-to-image translations do not control the output domain beyond the classes used during training, nor do they interpolate between different domains well, leading to implausible results.
Wavelet-based Unsupervised Label-to-Image Translation
GeorgeEskandar/USIS-Unsupervised-Semantic-Image-Synthesis
•
•
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022
Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a semantic layout is used to generate a photorealistic image.
