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
Latest papers
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.
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.
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.
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.
Lifespan Age Transformation Synthesis
royorel/Lifespan_Age_Transformation_Synthesis
•
•
ECCV 2020
Most existing aging methods are limited to changing the texture, overlooking transformations in head shape that occur during the human aging and growth process.
High-Resolution Daytime Translation Without Domain Labels
We present the high-resolution daytime translation (HiDT) model for this task.
StarGAN v2: Diverse Image Synthesis for Multiple Domains
clovaai/stargan-v2
•
•
CVPR 2020
A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains.
Breaking the cycle -- Colleagues are all you need
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.
Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis
In this work, we propose a simple yet effective regularization term to address the mode collapse issue for cGANs.
Diverse Image-to-Image Translation via Disentangled Representations
HsinYingLee/DRIT
•
•
ECCV 2018
Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time.
