Weamba: Weather-Degraded Remote Sensing Image Restoration with Multi-Router State Space Model
Open Access
- 29 January 2025
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 17 (3) , 458
Abstract
Adverse weather conditions, such as haze and raindrop, consistently degrade the quality of remote sensing images and affect subsequent vision-based applications. Recent years have witnessed advancements in convolutional neural networks (CNNs) and Transformers in the field of remote sensing image restoration. However, these methods either suffer from limited receptive fields or incur quadratic computational overhead, leading to an imbalance between performance and model efficiency. In this paper, we propose an effective vision state space model (called Weamba) for remote sensing image restoration by modeling long-range pixel dependencies with linear complexity. Specifically, we develop a local-enhanced state space module to better aggregate rich local and global information, both of which are complementary and beneficial for high-quality image reconstruction. Furthermore, we design a multi-router scanning strategy for spatially varying feature extraction, alleviating the issue of redundant information caused by repeated scanning directions in existing methods. Extensive experiments on multiple benchmarks show that the proposed Weamba performs favorably against state-of-the-art approaches.Keywords
This publication has 39 references indexed in Scilit:
- Multi-scale transformer with conditioned prompt for image derainingDigital Signal Processing, 2024
- Improving Skip Connection in U-Net Through Fusion Perspective With Mamba for Image DehazingIEEE Transactions on Consumer Electronics, 2024
- Encoder-Free Multiaxis Physics-Aware Fusion Network for Remote Sensing Image DehazingIEEE Transactions on Geoscience and Remote Sensing, 2023
- Learning an Effective Transformer for Remote Sensing Satellite Image DehazingIEEE Geoscience and Remote Sensing Letters, 2023
- Toward Blind-Adaptive Remote Sensing Image RestorationIEEE Transactions on Geoscience and Remote Sensing, 2023
- M2SCN: Multi-Model Self-Correcting Network for Satellite Remote Sensing Single-Image DehazingIEEE Geoscience and Remote Sensing Letters, 2022
- Image Restoration for Remote Sensing: Overview and toolboxIEEE Geoscience and Remote Sensing Magazine, 2021
- Hybrid High-Resolution Learning for Single Remote Sensing Satellite Image DehazingIEEE Geoscience and Remote Sensing Letters, 2021
- A Coarse-to-Fine Two-Stage Attentive Network for Haze Removal of Remote Sensing ImagesIEEE Geoscience and Remote Sensing Letters, 2020
- Single Remote Sensing Image DehazingIEEE Geoscience and Remote Sensing Letters, 2013