Image-to-Image Translation
491 papers with code • 37 benchmarks • 29 datasets
Image-to-Image Translation is a task in computer vision and machine learning where the goal is to learn a mapping between an input image and an output image, such that the output image can be used to perform a specific task, such as style transfer, data augmentation, or image restoration.
( Image credit: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks )
Benchmarks
These leaderboards are used to track progress in Image-to-Image Translation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Image-to-Image Translation models and implementationsDatasets
Cityscapes
KITTI
ADE20K
CelebA-HQ
SYNTHIA
GTA5
DeepFashion
Perceptual Similarity
AFHQ
COCO-Stuff
Subtasks
Latest papers
Radio-astronomical Image Reconstruction with Conditional Denoising Diffusion Model
mariiadrozdova/diffusion-for-sources-characterisation
•
•
Current techniques, such as CLEAN and PyBDSF, often fail to detect faint sources, highlighting the need for more accurate methods.
BlenDA: Domain Adaptive Object Detection through diffusion-based blending
aiiu-lab/blenda
•
•
Unsupervised domain adaptation (UDA) aims to transfer a model learned using labeled data from the source domain to unlabeled data in the target domain.
Contrastive Learning-Based Framework for Sim-to-Real Mapping of Lidar Point Clouds in Autonomous Driving Systems
Motivated by this potential, this paper focuses on sim-to-real mapping of Lidar point clouds, a widely used perception sensor in automated driving systems.
PhenDiff: Revealing Invisible Phenotypes with Conditional Diffusion Models
warmongeringbeaver/phendiff
•
•
Furthermore, the lack of robustness to invert a real image into the latent of a trained GAN prevents flexible editing of real images.
Open-DDVM: A Reproduction and Extension of Diffusion Model for Optical Flow Estimation
dqiaole/flowdiffusion_pytorch
•
•
Recently, Google proposes DDVM which for the first time demonstrates that a general diffusion model for image-to-image translation task works impressively well on optical flow estimation task without any specific designs like RAFT.
STEREOFOG -- Computational DeFogging via Image-to-Image Translation on a real-world Dataset
Image-to-Image translation (I2I) is a subtype of Machine Learning (ML) that has tremendous potential in applications where two domains of images and the need for translation between the two exist, such as the removal of fog.
Towards Unsupervised Representation Learning: Learning, Evaluating and Transferring Visual Representations
Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals.
MicroGlam: Microscopic Skin Image Dataset with Cosmetics
We repeated the process for the same skin patch under three cosmetic products.
Fine-grained Appearance Transfer with Diffusion Models
babahui/fine-grained-appearance-transfer
•
•
A pivotal aspect of our approach is the strategic use of the predicted $x_0$ space by diffusion models within the latent space of diffusion processes.
A deep learning approach for marine snow synthesis and removal
Marine snow, the floating particles in underwater images, severely degrades the visibility and performance of human and machine vision systems.
