MFEM: Multiscale Frequency-Enhanced Mamba for Lightweight Remote Sensing Image Super-Resolution
- 10 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Abstract
In recent years, remarkable progress has been achieved in lightweight Remote Sensing Image Super-Resolution (RSISR) techniques. However, these methods, in order to maintain lightweight property and efficient computation, are often affected by inadequate feature extraction and limited receptive fields, which restrict the precise reconstruction of structurally complex remote sensing images (RSI). To address this issue, we propose a Multi-Scale Frequency-Enhanced Mamba (MFEM), which employs a unique multi-scale convolutional structure to enhance feature extraction and utilizes a frequency-enhanced Mamba to capture long-range dependencies with linear complexity. Specifically, we design a Multi-Scale Blueprint Residual Block (MBRB) with three specifications, which allows the network to efficiently extract multi-scale features of RSIs while maintaining lightweight property by using different specifications of MBRB at varying network depths. Furthermore, we develop a Frequency Mamba Enhancement Block (FMEB), which enhances Mamba from within through frequency analysis to globally model multi-level features while improving local information loss. Extensive experiments demonstrate that our method achieves better super-resolution performance while maintaining lightweight property.Keywords
Funding Information
- Henan science and technology development plan project (242102210064)
- National Natural Science Foundation of China (12201185)
This publication has 17 references indexed in Scilit:
- SMFANet: A Lightweight Self-Modulation Feature Aggregation Network for Efficient Image Super-Resolution2024
- MambaIR: A Simple Baseline for Image Restoration with State-Space Model2024
- Hybrid Attention-Based U-Shaped Network for Remote Sensing Image Super-ResolutionIEEE Transactions on Geoscience and Remote Sensing, 2023
- Omni Aggregation Networks for Lightweight Image Super-Resolution2023
- Blueprint Separable Residual Network for Efficient Image Super-Resolution2022
- FeNet: Feature Enhancement Network for Lightweight Remote-Sensing Image Super-ResolutionIEEE Transactions on Geoscience and Remote Sensing, 2022
- Residual Feature Aggregation Network for Image Super-Resolution2020
- Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets2020
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Deep Learning Based Feature Selection for Remote Sensing Scene ClassificationIEEE Geoscience and Remote Sensing Letters, 2015