# Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis

arXiv: https://arxiv.org/abs/2603.21661 · HTML: https://mlsanity.com/paper/2603.21661/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 65 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 30 of 35)

- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Deep Joint Rain Detection and Removal from a Single Image](https://mlsanity.com/paper/1609.07769/) (2016)
- [Density-aware Single Image De-raining using a Multi-stream Dense Network](https://mlsanity.com/paper/1802.07412/) (2018)
- [Learning A Sparse Transformer Network for Effective Image Deraining](https://mlsanity.com/paper/2303.11950/) (2023)
- [Image De-raining Using a Conditional Generative Adversarial Network](https://mlsanity.com/paper/1701.05957/) (2017)
- [Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset](https://mlsanity.com/paper/1904.01538/) (2019)
- [Clearing the Skies: A deep network architecture for single-image rain removal](https://mlsanity.com/paper/1609.02087/) (2016)
- [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)
- [Structure-Preserving Deraining with Residue Channel Prior Guidance](https://mlsanity.com/paper/2108.09079/) (2021)
- [Syn2Real Transfer Learning for Image Deraining using Gaussian Processes](https://mlsanity.com/paper/2006.05580/) (2020)
- [Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining](https://mlsanity.com/paper/2404.01547/) (2024)
- [DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal](https://mlsanity.com/paper/2008.00767/) (2020)
- [Toward Real-world Single Image Deraining: A New Benchmark and Beyond](https://mlsanity.com/paper/2206.05514/) (2022)
- [Towards Unified Deep Image Deraining: A Survey and A New Benchmark](https://mlsanity.com/paper/2310.03535/) (2023)
- [Semi-Supervised Video Deraining with Dynamical Rain Generator](https://mlsanity.com/paper/2103.07939/) (2021)
- [Not Just Streaks: Towards Ground Truth for Single Image Deraining](https://mlsanity.com/paper/2206.10779/) (2022)
- [Unsupervised Single Image Deraining with Self-supervised Constraints](https://mlsanity.com/paper/1811.08575/) (2018)
- [SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection](https://mlsanity.com/paper/2403.05416/) (2024)
- [IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images](https://mlsanity.com/paper/2403.11870/) (2024)
- [Multi-pseudo Regularized Label for Generated Data in Person Re-Identification](https://mlsanity.com/paper/1801.06742/) (2018)
- [Unsupervised Image Deraining: Optimization Model Driven Deep CNN](https://mlsanity.com/paper/2203.13699/) (2022)
- [NiteDR: Nighttime Image De-Raining with Cross-View Sensor Cooperative Learning for Dynamic Driving Scenes](https://mlsanity.com/paper/2402.18172/) (2024)
- [Single Image Deraining using Scale-Aware Multi-Stage Recurrent Network](https://mlsanity.com/paper/1712.06830/) (2017)
- [Single Image Deraining with Continuous Rain Density Estimation](https://mlsanity.com/paper/2006.03190/) (2020)
- [Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining](https://mlsanity.com/paper/2505.16811/) (2025)

## Abstract (arXiv)

Image deraining plays a pivotal role in low-level computer vision, serving as a prerequisite for robust outdoor surveillance and autonomous driving systems. While deep learning paradigms have achieved remarkable success in firmly aligned settings, they often suffer from severe performance degradation when generalized to unseen Out-of-Distribution (OOD) scenarios. This failure stems primarily from the significant domain discrepancy between synthetic training datasets and the complex physical dynamics of real-world rain. To address these challenges, this paper proposes a pioneering cross-scenario deraining adaptation framework. Diverging from conventional approaches, our method obviates the requirements for paired rainy observations in the target domain, leveraging exclusively rain-free background images. We design a Superpixel Generation (Sup-Gen) module to extract stable structural priors from the source domain using Simple Linear Iterative Clustering. Subsequently, a Resolution-adaptive Fusion strategy is introduced to align these source structures with target backgrounds through texture similarity, ensuring the synthesis of diverse and realistic pseudo-data. Finally, we implement a pseudo-label re-Synthesize mechanism that employs multi-stage noise generation to simulate realistic rain streaks. This framework functions as a versatile plug-and-play module capable of seamless integration into arbitrary deraining architectures. Extensive experiments on state-of-the-art models demonstrate that our approach yields remarkable PSNR gains of up to 32% to 59% in OOD domains while significantly accelerating training convergence.