# Joint Self-Attention and Scale-Aggregation for Self-Calibrated Deraining Network

arXiv: https://arxiv.org/abs/2008.02763 · HTML: https://mlsanity.com/paper/2008.02763/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2020.

## Built on by (most cited first, 25 of 25)

- [Structure-Preserving Deraining with Residue Channel Prior Guidance](https://mlsanity.com/paper/2108.09079/) (2021)
- [Towards Unified Deep Image Deraining: A Survey and A New Benchmark](https://mlsanity.com/paper/2310.03535/) (2023)
- [Visible Watermark Removal via Self-calibrated Localization and Background Refinement](https://mlsanity.com/paper/2108.03581/) (2021)
- [Networks are Slacking Off: Understanding Generalization Problem in Image Deraining](https://mlsanity.com/paper/2305.15134/) (2023)
- [Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution](https://mlsanity.com/paper/2406.13607/) (2024)
- [Online-updated High-order Collaborative Networks for Single Image Deraining](https://mlsanity.com/paper/2202.06568/) (2022)
- [Unpaired Photo-realistic Image Deraining with Energy-informed Diffusion Model](https://mlsanity.com/paper/2407.17193/) (2024)
- [Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks](https://mlsanity.com/paper/2406.00721/) (2024)
- [Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey](https://mlsanity.com/paper/2505.16161/) (2025)
- [Single Image Deraining Network with Rain Embedding Consistency and Layered LSTM](https://mlsanity.com/paper/2111.03615/) (2021)
- [Attention and Self-Attention in Random Forests](https://mlsanity.com/paper/2207.04293/) (2022)
- [Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining](https://mlsanity.com/paper/2502.12600/) (2025)
- [A comprehensive benchmark analysis for sand dust image reconstruction](https://mlsanity.com/paper/2202.03031/) (2022)
- [SDNet: mutil-branch for single image deraining using swin](https://mlsanity.com/paper/2105.15077/) (2021)
- [Learning A Coarse-to-Fine Diffusion Transformer for Image Restoration](https://mlsanity.com/paper/2308.08730/) (2023)
- [Adapting Large VLMs with Iterative and Manual Instructions for Generative Low-light Enhancement](https://mlsanity.com/paper/2507.18064/) (2025)
- [TRNR: Task-Driven Image Rain and Noise Removal with a Few Images Based on Patch Analysis](https://mlsanity.com/paper/2112.01924/) (2021)
- [How Powerful Potential of Attention on Image Restoration?](https://mlsanity.com/paper/2403.10336/) (2024)
- [SpikeDerain: Unveiling Clear Videos from Rainy Sequences Using Color Spike Streams](https://mlsanity.com/paper/2503.20315/) (2025)
- [Degradation-Aware Prompt Learning with Cross-Modal Compensation for Adverse Weather Removal](https://mlsanity.com/paper/2608.06939/) (2026)
- [Ensemble-Based Survival Models with the Self-Attended Beran Estimator Predictions](https://mlsanity.com/paper/2506.07933/) (2025)
- [Multi-Modal Object Re-Identification with Prompt-S6 and Semantic-Aware Knowledge Guidance](https://mlsanity.com/paper/2607.23451/) (2026)
- [What to Remove, What to Preserve: Dual-Ambiguity Rectification for All-in-One Image Restoration](https://mlsanity.com/paper/2607.28526/) (2026)
- [Multi-Modal Object Re-Identification with Dual Semantic Guidance and Global-Local Mutual Modulation](https://mlsanity.com/paper/2607.29207/) (2026)
- [Ultra-High-Definition Restoration Transformers with Correlation Matching Transformation](https://mlsanity.com/paper/2608.20263/) (2026)

## Abstract (arXiv)

In the field of multimedia, single image deraining is a basic pre-processing work, which can greatly improve the visual effect of subsequent high-level tasks in rainy conditions. In this paper, we propose an effective algorithm, called JDNet, to solve the single image deraining problem and conduct the segmentation and detection task for applications. Specifically, considering the important information on multi-scale features, we propose a Scale-Aggregation module to learn the features with different scales. Simultaneously, Self-Attention module is introduced to match or outperform their convolutional counterparts, which allows the feature aggregation to adapt to each channel. Furthermore, to improve the basic convolutional feature transformation process of Convolutional Neural Networks (CNNs), Self-Calibrated convolution is applied to build long-range spatial and inter-channel dependencies around each spatial location that explicitly expand fields-of-view of each convolutional layer through internal communications and hence enriches the output features. By designing the Scale-Aggregation and Self-Attention modules with Self-Calibrated convolution skillfully, the proposed model has better deraining results both on real-world and synthetic datasets. Extensive experiments are conducted to demonstrate the superiority of our method compared with state-of-the-art methods. The source code will be available at urlhttps://supercong94.wixsite.com/supercong94.