Git Product home page Git Product logo

unpaired-low-level-vision-zoo's Introduction

Unpaired-Low-Level-Vision-Zoo Awesome

By Xiang Chen, Jiyang Lu.

A collection of awesome learning-based LLCV methods from unpaired data.

If you find some overlooked papers, please open issues or pull requests (recommended).

The following content is constantly updated, welcome continuous attention!

Related Works

Image Dehazing

  • You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network (IJCV2021) [paper][code]
  • Unsupervised Neural Rendering for Image Hazing (Arxiv2021) [paper]
  • DAMix: Density-Aware Data Augmentation for Unsupervised Domain Adaptation on Single Image Dehazing (Arxiv2021) [paper]
  • Zero-Shot Image Dehazing (TIP2020) [paper][code]
  • From Synthetic to Real Image Dehazing Collaborating with Unlabeled Real Data (ACMMM2021) [paper][code]
  • Unsupervised Conditional Disentangle Network For Image Dehazing (ICIP2020 ) [paper]
  • Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision (Arxiv2020) [paper]
  • Dehaze-GLCGAN: Unpaired Single Image De-hazing via Adversarial Training (Arxiv2020) [paper]
  • CDNet: Single Image De-hazing using Unpaired Adversarial Training (WACV2019) [paper]
  • Towards Perceptual Image Dehazing by Physics-Based Disentanglement and Adversarial Training (AAAI2018) [paper][code]
  • Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing (CVPRW2018) [paper]

Image Deraining

  • Unpaired Learning for Deep Image Deraining with Rain Direction Regularizer (ICCV2021) [paper][code]
  • Unpaired Adversarial Learning for Single Image Deraining with Rain-Space Contrastive Constraints (Arxiv2021) [paper]
  • Decomposed Cyclegan for Single Image Deraining With Unpaired Data (ICASSP2020) [paper]
  • Singe Image Rain Removal with Unpaired Information A Differentiable Programming Perspective (AAAI2019) [paper]
  • DerainCycleGAN: A Simple Unsupervised Network for Single Image Deraining and Rainmaking (Arviv2019) [paper]
  • Unsupervised Single Image Deraining with Self-supervised Constraints (ICIP2019) [paper]

Image Denoising

  • Unpaired Learning of Deep Image Denoising (ECCV2020) [paper][code]
  • End-to-End Unpaired Image Denoising with Conditional Adversarial Networks (AAAI2020) [paper][code]
  • Unpaired Image Denoising (Arxiv2020) [paper]

Image Enhancement

  • Enhance Image as You Like with Unpaired Learning (IJCAI2021) [paper][code]
  • EnlightenGAN: Deep Light Enhancement without Paired Supervision (TIP2021) [paper][code]
  • Unpaired Image Enhancement with Quality-Attention Generative Adversarial Network (ACMMM2020) [paper]
  • Global and Local Enhancement Networks for Paired and Unpaired Image Enhancement (ECCV2020) [paper]
  • Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs (CVPR2018) [paper][code]

Image Translation

  • Unpaired Image-to-Image Translation via Latent Energy Transport (CVPR2021) [paper][code]
  • Memory-Guided Unsupervised Image-to-Image Translation (CVPR2021) [paper]
  • Dual Contrastive Learning for Unsupervised Image-to-Image Translation (CVPRW2021) [paper]
  • Rethinking the Truly Unsupervised Image-to-Image Translation (ICCV2021) [paper]
  • Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation (ICCV2021) [paper]
  • Semantically Robust Unpaired Image Translation for Data with Unmatched Semantics Statistics (ICCV2021) [paper]
  • Deformation-Aware Unpaired Image Translation for Pose Estimation on Laboratory Animals (CVPR2020) [paper]
  • DUNIT: Detection-Based Unsupervised Image-to-Image Translation (CVPR2020) [paper]
  • Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation (CVPR2020) [paper][code]
  • One-to-one Mapping for Unpaired Image-to-image Translation (WACV2020) [paper]
  • Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptation (WACV2020) [paper]
  • CrossNet: Latent Cross-Consistency for Unpaired Image Translation (WACV2020) [paper]
  • Homomorphic Latent Space Interpolation for Unpaired Image-to-image Translation (CVPR2019) [paper]
  • TransGaGa: Geometry-Aware Unsupervised Image-To-Image Translation (CVPR2019) [paper][code]
  • Few-Shot Unsupervised Image-to-Image Translation (ICCV2019) [paper][code]
  • Co-Evolutionary Compression for Unpaired Image Translation (ICCV2019) [paper]
  • Attribute-Driven Spontaneous Motion in Unpaired Image Translation (ICCV2019) [paper]

Others

  • DeFlow: Learning Complex Image Degradations From Unpaired Data With Conditional Flows (CVPR2021) [paper]
  • Light Source Guided Single-Image Flare Removal from Unpaired Data (ICCV2021) [paper]
  • Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data (ICCV2019) [paper]

unpaired-low-level-vision-zoo's People

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.