# Unsupervised Image Deraining: Optimization Model Driven Deep CNN

arXiv: https://arxiv.org/abs/2203.13699 · HTML: https://mlsanity.com/paper/2203.13699/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 48 references that are in the map.
- First posted on arXiv 25 Mar 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [Deep Joint Rain Detection and Removal from a Single Image](https://mlsanity.com/paper/1609.07769/) (2016)
- [Progressive Image Deraining Networks: A Better and Simpler Baseline](https://mlsanity.com/paper/1901.09221/) (2019)
- [Multi-Scale Progressive Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2003.10985/) (2020)
- [Density-aware Single Image De-raining using a Multi-stream Dense Network](https://mlsanity.com/paper/1802.07412/) (2018)
- [Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining](https://mlsanity.com/paper/1807.05698/) (2018)
- [Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset](https://mlsanity.com/paper/1904.01538/) (2019)
- [Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning](https://mlsanity.com/paper/1904.05050/) (2019)
- [A Model-driven Deep Neural Network for Single Image Rain Removal](https://mlsanity.com/paper/2005.01333/) (2020)
- [Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining](https://mlsanity.com/paper/1906.11129/) (2019)
- [Single Image Deraining: From Model-Based to Data-Driven and Beyond](https://mlsanity.com/paper/1912.07150/) (2019)
- [Syn2Real Transfer Learning for Image Deraining using Gaussian Processes](https://mlsanity.com/paper/2006.05580/) (2020)
- [Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework](https://mlsanity.com/paper/1803.10433/) (2018)
- [Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation](https://mlsanity.com/paper/2103.13660/) (2021)
- [Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining](https://mlsanity.com/paper/1808.01491/) (2018)
- [Conditional Variational Image Deraining](https://mlsanity.com/paper/2004.11373/) (2020)
- [DTDN: Dual-task De-raining Network](https://mlsanity.com/paper/2008.09326/) (2020)
- [Single Image Deraining via Scale-space Invariant Attention Neural Network](https://mlsanity.com/paper/2006.05049/) (2020)

## Built on by (most cited first, 12 of 12)

- [Towards Unified Deep Image Deraining: A Survey and A New Benchmark](https://mlsanity.com/paper/2310.03535/) (2023)
- [Unpaired Photo-realistic Image Deraining with Energy-informed Diffusion Model](https://mlsanity.com/paper/2407.17193/) (2024)
- [RainyScape: Unsupervised Rainy Scene Reconstruction using Decoupled Neural Rendering](https://mlsanity.com/paper/2404.11401/) (2024)
- [Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity](https://mlsanity.com/paper/2211.00837/) (2022)
- [NeurTV: Total Variation on the Neural Domain](https://mlsanity.com/paper/2405.17241/) (2024)
- [Re-boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restoration](https://mlsanity.com/paper/2408.09241/) (2024)
- [DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video Deraining](https://mlsanity.com/paper/2509.21719/) (2025)
- [Cycle Contrastive Adversarial Learning for Unsupervised image Deraining](https://mlsanity.com/paper/2407.11750/) (2024)
- [Data-free Distillation with Degradation-prompt Diffusion for Multi-weather Image Restoration](https://mlsanity.com/paper/2409.03455/) (2024)
- [MDeRainNet: An Efficient Macro-pixel Image Rain Removal Network](https://mlsanity.com/paper/2406.10652/) (2024)
- [TDiR: Transformer based Diffusion for Image Restoration Tasks](https://mlsanity.com/paper/2506.20302/) (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)

The deep convolutional neural network has achieved significant progress for single image rain streak removal. However, most of the data-driven learning methods are full-supervised or semi-supervised, unexpectedly suffering from significant performance drops when dealing with real rain. These data-driven learning methods are representative yet generalize poor for real rain. The opposite holds true for the model-driven unsupervised optimization methods. To overcome these problems, we propose a unified unsupervised learning framework which inherits the generalization and representation merits for real rain removal. Specifically, we first discover a simple yet important domain knowledge that directional rain streak is anisotropic while the natural clean image is isotropic, and formulate the structural discrepancy into the energy function of the optimization model. Consequently, we design an optimization model-driven deep CNN in which the unsupervised loss function of the optimization model is enforced on the proposed network for better generalization. In addition, the architecture of the network mimics the main role of the optimization models with better feature representation. On one hand, we take advantage of the deep network to improve the representation. On the other hand, we utilize the unsupervised loss of the optimization model for better generalization. Overall, the unsupervised learning framework achieves good generalization and representation: unsupervised training (loss) with only a few real rainy images (input) and physical meaning network (architecture). Extensive experiments on synthetic and real-world rain datasets show the superiority of the proposed method.