# Unsupervised Single Image Deraining with Self-supervised Constraints

arXiv: https://arxiv.org/abs/1811.08575 · HTML: https://mlsanity.com/paper/1811.08575/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2018.

## Built on by (most cited first, 19 of 19)

- [Unpaired Deep Image Deraining Using Dual Contrastive Learning](https://mlsanity.com/paper/2109.02973/) (2021)
- [WaveDM: Wavelet-Based Diffusion Models for Image Restoration](https://mlsanity.com/paper/2305.13819/) (2023)
- [Towards Unified Deep Image Deraining: A Survey and A New Benchmark](https://mlsanity.com/paper/2310.03535/) (2023)
- [Unsupervised Deraining: Where Contrastive Learning Meets Self-similarity](https://mlsanity.com/paper/2203.11509/) (2022)
- [Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches](https://mlsanity.com/paper/2308.06776/) (2023)
- [RCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining](https://mlsanity.com/paper/2107.06808/) (2021)
- [Channel Consistency Prior and Self-Reconstruction Strategy Based Unsupervised Image Deraining](https://mlsanity.com/paper/2503.18703/) (2025)
- [Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity](https://mlsanity.com/paper/2211.00837/) (2022)
- [Re-boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restoration](https://mlsanity.com/paper/2408.09241/) (2024)
- [U-DuDoNet: Unpaired dual-domain network for CT metal artifact reduction](https://mlsanity.com/paper/2103.04552/) (2021)
- [Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN](https://mlsanity.com/paper/2204.10970/) (2022)
- [Cycle Contrastive Adversarial Learning for Unsupervised image Deraining](https://mlsanity.com/paper/2407.11750/) (2024)
- [DestripeCycleGAN: Stripe Simulation CycleGAN for Unsupervised Infrared Image Destriping](https://mlsanity.com/paper/2402.09101/) (2024)
- [Gabor-guided transformer for single image deraining](https://mlsanity.com/paper/2403.07380/) (2024)
- [Towards Better De-raining Generalization via Rainy Characteristics Memorization and Replay](https://mlsanity.com/paper/2506.02477/) (2025)
- [SD-PSFNet: Sequential and Dynamic Point Spread Function Network for Image Deraining](https://mlsanity.com/paper/2511.17993/) (2025)
- [Deep Single Image Deraining using An Asymetric Cycle Generative and Adversarial Framework](https://mlsanity.com/paper/2202.09635/) (2022)
- [Pseudo-Label Guided Real-World Image De-weathering: A Learning Framework with Imperfect Supervision](https://mlsanity.com/paper/2504.09949/) (2025)
- [Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis](https://mlsanity.com/paper/2603.21661/) (2026)

## Abstract (arXiv)

Most existing single image deraining methods require learning supervised models from a large set of paired synthetic training data, which limits their generality, scalability and practicality in real-world multimedia applications. Besides, due to lack of labeled-supervised constraints, directly applying existing unsupervised frameworks to the image deraining task will suffer from low-quality recovery. Therefore, we propose an Unsupervised Deraining Generative Adversarial Network (UD-GAN) to tackle above problems by introducing self-supervised constraints from the intrinsic statistics of unpaired rainy and clean images. Specifically, we firstly design two collaboratively optimized modules, namely Rain Guidance Module (RGM) and Background Guidance Module (BGM), to take full advantage of rainy image characteristics: The RGM is designed to discriminate real rainy images from fake rainy images which are created based on outputs of the generator with BGM. Simultaneously, the BGM exploits a hierarchical Gaussian-Blur gradient error to ensure background consistency between rainy input and de-rained output. Secondly, a novel luminance-adjusting adversarial loss is integrated into the clean image discriminator considering the built-in luminance difference between real clean images and derained images. Comprehensive experiment results on various benchmarking datasets and different training settings show that UD-GAN outperforms existing image deraining methods in both quantitative and qualitative comparisons.