Journal
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
Volume 59, Issue 2, Pages 1618-1633Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2020.2994253
Keywords
Image reconstruction; Remote sensing; Feature extraction; Spatial resolution; Convolutional neural networks; Attention mechanism; dense sampling; remote sensing image; super-resolution; wide activation
Categories
Funding
- National Natural Science Foundation of China [91638201, 41722108]
- National Key Research and Development Program of China [2016YFB0501501]
Ask authors/readers for more resources
The study introduces a dense-sampling super-resolution network for large-scale reconstruction of remote sensing images, improving network representation ability and performance through a wide feature attention block and chain training strategy, with extensive experiments demonstrating superior performance in both quantitative evaluation and visual quality compared to state-of-the-art models.
Super-resolution (SR) techniques play a crucial role in increasing the spatial resolution of remote sensing data and overcoming the physical limitations of the spaceborne imaging systems. Though the convolutional neural network (CNN)-based methods have obtained good performance, they show limited capacity when coping with large-scale super-resolving tasks. The more complicated spatial distribution of remote sensing data further increases the difficulty in reconstruction. This article develops a dense-sampling super-resolution network (DSSR) to explore the large-scale SR reconstruction of the remote sensing imageries. Specifically, a dense-sampling mechanism, which reuses an upscaler to upsample multiple low-dimension features, is presented to make the network jointly consider multilevel priors when performing reconstruction. A wide feature attention block (WAB), which incorporates the wide activation and attention mechanism, is introduced to enhance the representation ability of the network. In addition, a chain training strategy is proposed to optimize further the performance of the large-scale models by borrowing knowledge from the pretrained small-scale models. Extensive experiments demonstrate the effectiveness of the proposed methods and show that the DSSR outperforms the state-of-the-art models in both quantitative evaluation and visual quality.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available