Saved in:
Bibliographic Details
Main Authors: Xue, Pengze, Wang, Shanwen, Zhou, Fei, Cui, Yan, Sun, Xin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.26413
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915525490114560
author Xue, Pengze
Wang, Shanwen
Zhou, Fei
Cui, Yan
Sun, Xin
author_facet Xue, Pengze
Wang, Shanwen
Zhou, Fei
Cui, Yan
Sun, Xin
contents Image deraining is an essential vision technique that removes rain streaks and water droplets, enhancing clarity for critical vision tasks like autonomous driving. However, current single-scale models struggle with fine-grained recovery and global consistency. To address this challenge, we propose Progressive Rain removal with Integrated State-space Modeling (PRISM), a progressive three-stage framework: Coarse Extraction Network (CENet), Frequency Fusion Network (SFNet), and Refine Network (RNet). Specifically, CENet and SFNet utilize a novel Hybrid Attention UNet (HA-UNet) for multi-scale feature aggregation by combining channel attention with windowed spatial transformers. Moreover, we propose Hybrid Domain Mamba (HDMamba) for SFNet to jointly model spatial semantics and wavelet domain characteristics. Finally, RNet recovers the fine-grained structures via an original-resolution subnetwork. Our model learns high-frequency rain characteristics while preserving structural details and maintaining global context, leading to improved image quality. Our method achieves competitive results on multiple datasets against recent deraining methods.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26413
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PRISM: Progressive Rain removal with Integrated State-space Modeling
Xue, Pengze
Wang, Shanwen
Zhou, Fei
Cui, Yan
Sun, Xin
Computer Vision and Pattern Recognition
Image deraining is an essential vision technique that removes rain streaks and water droplets, enhancing clarity for critical vision tasks like autonomous driving. However, current single-scale models struggle with fine-grained recovery and global consistency. To address this challenge, we propose Progressive Rain removal with Integrated State-space Modeling (PRISM), a progressive three-stage framework: Coarse Extraction Network (CENet), Frequency Fusion Network (SFNet), and Refine Network (RNet). Specifically, CENet and SFNet utilize a novel Hybrid Attention UNet (HA-UNet) for multi-scale feature aggregation by combining channel attention with windowed spatial transformers. Moreover, we propose Hybrid Domain Mamba (HDMamba) for SFNet to jointly model spatial semantics and wavelet domain characteristics. Finally, RNet recovers the fine-grained structures via an original-resolution subnetwork. Our model learns high-frequency rain characteristics while preserving structural details and maintaining global context, leading to improved image quality. Our method achieves competitive results on multiple datasets against recent deraining methods.
title PRISM: Progressive Rain removal with Integrated State-space Modeling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.26413