GAN-Based Multi-level Mapping Network for Satellite Imagery Super-Resolution
Lists
Only you see this
Abstract
Although many deep-learning-based image super-resolution (SR) methods have been proposed, most of them assume that all hierarchical features share the unified mapping equations. They ignore the differences between mapping equations at different feature levels, and create an average effect of mapping prediction, thus poorly building the mapping relations between low resolution (LR) and high resolution (HR) spaces. In this paper, we propose a multi-level mapping framework along with the adversarial learning strategy, namely MMGAN, for satellite imageries SR reconstruction. We also construct a feature extraction and tuning block (FETB) for fine feature expression. In particular, a novel two-dimension dense unit (DU) and a mapping attention unit (MAU) are constructed for building multi-level mappings in different stages. With our strategies, an HR image is reconstructed directly from the input image using multi-level mappings. Extensive experiments on Kaggle Open Source Dataset and Jilin-1 video satellite images exhibit superior reconstruction performance when compared with the state-of-the-art SR approaches.
BibTeX
@inproceedings{jiang2019gan,
author = {Kui Jiang and Zhongyuan Wang and Peng Yi and Junjun Jiang and Guangcheng Wang and Zhen Han and Tao Lu},
title = {{GAN-Based Multi-level Mapping Network for Satellite Imagery Super-Resolution}},
booktitle = {ICME},
year = {2019},
doi = {10.1109/icme.2019.00097},
}Loading related content...