MAIN: Multibranch Attention Integration Network for Degraded Remote-Sensing Image Super-Resolution
Lists
Only you see this
Abstract
Remote sensing images (RSIs) are limited by low-resolution imaging and a variety of degradation effects, posing significant challenges for high-level visual tasks. Traditional deep learning-based super-resolution (SR) algorithms struggle to optimize these issues end-to-end, which inhibits the algorithm’s lightweight design and restricts its application in real-time scenarios. To address this, we introduce a multi-branch attention integration network (MAIN) for the degraded RSI SR. This network features two key functional components: the multi-scale feature perception (MsFP) module and the multi-branch attention integration block (MAIB). The MsFP module, a lightweight convolution-based architecture, is designed primarily to counteract degradation effects and depict low-dimensional features. MAIB, a multi-branch parallel layout, employs attention mechanisms to enable high-level semantic information extraction and context-aware learning. Furthermore, we utilize modulation transfer functions to emulate various degradation effects, thus creating a dedicated dataset for degraded RSI SR, called DeRSSA. Extensive experimental evidence shows that MAIN exceeds the performance of the existing state-of-the-art method for the degraded RSI SR task. Our code and dataset will be accessible at https://github.com/lbo0928/MAIN.
BibTeX
@article{liu2023main,
author = {Bo Liu and Ligang Li and Yuan Cao and Wenbo Zhou and Zengyi Li and Wei Ni and Zhen Yang},
title = {{MAIN: Multibranch Attention Integration Network for Degraded Remote-Sensing Image Super-Resolution}},
journal = {IEEE Geoscience and Remote Sensing Letters},
year = {2023},
doi = {10.1109/lgrs.2023.3317681},
}Loading related content...