Open Access

ARTICLE

Efficient Image Deraining through a Stage-Wise Dual-Residual Network with Cross-Dimensional Spatial Attention

Tiantian Wang^1,2, Zhihua Hu^3,*

1 School of Computer and Software Engineering, SIAS University, Zhengzhou, 451150, China
2 Henan Province Engineering Research Center for Intelligent Manufacturing and Digital Twin, Zhengzhou, 451150, China
3 School of Computer Science and Artificial Intelligence, Huanggang Normal University, Huanggang, 438000, China

* Corresponding Author: Zhihua Hu. Email:

(This article belongs to the Special Issue: Advances in AI-Driven Computational Modeling for Image Processing)

Computer Modeling in Engineering & Sciences 2025, 145(2), 2357-2381. https://doi.org/10.32604/cmes.2025.073640

Received 22 September 2025; Accepted 29 October 2025; Issue published 26 November 2025

Abstract

Rain streaks introduced by atmospheric precipitation significantly degrade image quality and impair the reliability of high-level vision tasks. We present a novel image deraining framework built on a three-stage dual-residual architecture that progressively restores rain-degraded content while preserving fine structural details. Each stage begins with a multi-scale feature extractor and a channel attention module that adaptively emphasizes informative representations for rain removal. The core restoration is achieved via enhanced dual-residual blocks, which stabilize training and mitigate feature degradation across layers. To further refine representations, we integrate cross-dimensional spatial attention supervised by ground-truth guidance, ensuring that only high-quality features propagate to subsequent stages. Inter-stage feature fusion modules are employed to aggregate complementary information, reinforcing reconstruction continuity and consistency. Extensive experiments on five benchmark datasets (Rain100H, Rain100L, RainKITTI2012, RainKITTI2015, and JRSRD) demonstrate that our method establishes new state-of-the-art results in both fidelity and perceptual quality, effectively removing rain streaks while preserving natural textures and structural integrity.

---

Keywords

---