Saved in:
Bibliographic Details
Main Authors: Zou, Shun, Zou, Yi, Li, Juncheng, Gao, Guangwei, Qi, Guojun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.16455
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917412353343488
author Zou, Shun
Zou, Yi
Li, Juncheng
Gao, Guangwei
Qi, Guojun
author_facet Zou, Shun
Zou, Yi
Li, Juncheng
Gao, Guangwei
Qi, Guojun
contents Transformer-based networks have achieved strong performance in low-level vision tasks like image deraining by utilizing spatial or channel-wise self-attention. However, irregular rain patterns and complex geometric overlaps challenge single-paradigm architectures, necessitating a unified framework to integrate complementary global-local and spatial-channel representations. To address this, we propose a novel Cross Paradigm Representation and Alignment Transformer (CPRAformer). Its core idea is the hierarchical representation and alignment, leveraging the strengths of both paradigms (spatial-channel and global-local) to aid image reconstruction. It bridges the gap within and between paradigms, aligning and coordinating them to enable deep interaction and fusion of features. Specifically, we use two types of self-attention in the Transformer blocks: sparse prompt channel self-attention (SPC-SA) and spatial pixel refinement self-attention (SPR-SA). SPC-SA enhances global channel dependencies through dynamic sparsity, while SPR-SA focuses on spatial rain distribution and fine-grained texture recovery. To address the feature misalignment and knowledge differences between them, we introduce the Adaptive Alignment Frequency Module (AAFM), which aligns and interacts with features in a two-stage progressive manner, enabling adaptive guidance and complementarity. This reduces the information gap within and between paradigms. Through this unified cross-paradigm dynamic interaction framework, we achieve the extraction of the most valuable interactive fusion information from the two paradigms. Extensive experiments demonstrate that our model achieves state-of-the-art performance on eight benchmark datasets and further validates CPRAformer's robustness in other image restoration tasks and downstream applications.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16455
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cross Paradigm Representation and Alignment Transformer for Image Deraining
Zou, Shun
Zou, Yi
Li, Juncheng
Gao, Guangwei
Qi, Guojun
Computer Vision and Pattern Recognition
Transformer-based networks have achieved strong performance in low-level vision tasks like image deraining by utilizing spatial or channel-wise self-attention. However, irregular rain patterns and complex geometric overlaps challenge single-paradigm architectures, necessitating a unified framework to integrate complementary global-local and spatial-channel representations. To address this, we propose a novel Cross Paradigm Representation and Alignment Transformer (CPRAformer). Its core idea is the hierarchical representation and alignment, leveraging the strengths of both paradigms (spatial-channel and global-local) to aid image reconstruction. It bridges the gap within and between paradigms, aligning and coordinating them to enable deep interaction and fusion of features. Specifically, we use two types of self-attention in the Transformer blocks: sparse prompt channel self-attention (SPC-SA) and spatial pixel refinement self-attention (SPR-SA). SPC-SA enhances global channel dependencies through dynamic sparsity, while SPR-SA focuses on spatial rain distribution and fine-grained texture recovery. To address the feature misalignment and knowledge differences between them, we introduce the Adaptive Alignment Frequency Module (AAFM), which aligns and interacts with features in a two-stage progressive manner, enabling adaptive guidance and complementarity. This reduces the information gap within and between paradigms. Through this unified cross-paradigm dynamic interaction framework, we achieve the extraction of the most valuable interactive fusion information from the two paradigms. Extensive experiments demonstrate that our model achieves state-of-the-art performance on eight benchmark datasets and further validates CPRAformer's robustness in other image restoration tasks and downstream applications.
title Cross Paradigm Representation and Alignment Transformer for Image Deraining
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.16455