# Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks

arXiv: https://arxiv.org/abs/2406.00721 · HTML: https://mlsanity.com/paper/2406.00721/

## Key facts

- Cited by 7 papers in the map (data through 7 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 2 Jun 2024.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [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)
- [A Model-driven Deep Neural Network for Single Image Rain Removal](https://mlsanity.com/paper/2005.01333/) (2020)
- [Neural Nearest Neighbors Networks](https://mlsanity.com/paper/1810.12575/) (2018)
- [Cross-Scale Internal Graph Neural Network for Image Super-Resolution](https://mlsanity.com/paper/2006.16673/) (2020)
- [Single Image Deraining: A Comprehensive Benchmark Analysis](https://mlsanity.com/paper/1903.08558/) (2019)
- [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022)
- [Syn2Real Transfer Learning for Image Deraining using Gaussian Processes](https://mlsanity.com/paper/2006.05580/) (2020)
- [DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal](https://mlsanity.com/paper/2008.00767/) (2020)
- [Gated Channel Transformation for Visual Recognition](https://mlsanity.com/paper/1909.11519/) (2019)
- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [Structure Representation Network and Uncertainty Feedback Learning for Dense Non-Uniform Fog Removal](https://mlsanity.com/paper/2210.03061/) (2022)
- [Joint Self-Attention and Scale-Aggregation for Self-Calibrated Deraining Network](https://mlsanity.com/paper/2008.02763/) (2020)
- [SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency](https://mlsanity.com/paper/2303.07033/) (2023)
- [Online-updated High-order Collaborative Networks for Single Image Deraining](https://mlsanity.com/paper/2202.06568/) (2022)
- [Physical Model Guided Deep Image Deraining](https://mlsanity.com/paper/2003.13242/) (2020)
- [Dual Inverse Degradation Network for Real-World SDRTV-to-HDRTV Conversion](https://mlsanity.com/paper/2307.03394/) (2023)
- [How Powerful Potential of Attention on Image Restoration?](https://mlsanity.com/paper/2403.10336/) (2024)

## Built on by (most cited first, 7 of 7)

- [Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution](https://mlsanity.com/paper/2406.13607/) (2024)
- [Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey](https://mlsanity.com/paper/2505.16161/) (2025)
- [Rethinking Nighttime Image Deraining via Learnable Color Space Transformation](https://mlsanity.com/paper/2510.17440/) (2025)
- [Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement](https://mlsanity.com/paper/2507.18064/) (2025)
- [Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers](https://mlsanity.com/paper/2604.04630/) (2026)
- [DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration](https://mlsanity.com/paper/2606.19097/) (2026)
- [Degradation-Aware Prompt Learning with Cross-Modal Compensation for Adverse Weather Removal](https://mlsanity.com/paper/2608.06939/) (2026)

## Abstract (arXiv)

Patch-level non-local self-similarity is an important property of natural images. However, most existing methods do not consider this property into neural networks for image deraining, thus affecting recovery performance. Motivated by this property, we find that there exists significant patch recurrence property of a rainy image, that is, similar patches tend to recur many times in one image and its multi-scale images and external images. To better model this property for image detaining, we develop a multi-scale graph network with exemplars, called MSGNN, that contains two branches: 1) internal data-based supervised branch is used to model the internal relations of similar patches from the rainy image itself and its multi-scale images and 2) external data-participated unsupervised branch is used to model the external relations of the similar patches in the rainy image and exemplar. Specifically, we construct a graph model by searching the k-nearest neighboring patches from both the rainy images in a multi-scale framework and the exemplar. After obtaining the corresponding k neighboring patches from the multi-scale images and exemplar, we build a graph and aggregate them in an attentional manner so that the graph can provide more information from similar patches for image deraining. We embed the proposed graph in a deep neural network and train it in an end-to-end manner. Extensive experiments demonstrate that the proposed algorithm performs favorably against eight state-of-the-art methods on five public synthetic datasets and one real-world dataset. The source codes will be available at https://github.com/supersupercong/MSGNN.