Abstract | ||
---|---|---|
Recently, single image super-resolution (SR) methods based on deep convolutional neural network (CNN) have demonstrated remarkable progress. The essence of most CNN-based models is to learn the non-linear mapping between low-resolution patches and corresponding high-resolution ones. However, numerous convolutions are applied to implement this mapping, which directly contributes to large model sizes and huge graphics memory consumption. In this paper, we propose a lightweight feature enhancement residual network (FERN) to achieve prominent performance by incorporating lightweight non-local operations into the residual block. By taking advantage of utilizing this non-locally enhanced residual block, the proposed model can capture long-range dependencies. For further improving performance, we design the structure-aware channel attention layer that explicitly boosts feature maps with more structural and textural details. Extensive experiments suggest that the proposed approach performs favorably against the state-of-the-art SR algorithms in terms of visual quality and inference time. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.neucom.2020.05.008 | Neurocomputing |
Keywords | DocType | Volume |
Lightweight image super-resolution,Non-locally enhanced module,Structure-aware channel attention | Journal | 404 |
ISSN | Citations | PageRank |
0925-2312 | 4 | 0.39 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hui Zheng | 1 | 73 | 15.94 |
Xinbo Gao | 2 | 5534 | 344.56 |
Xiumei Wang | 3 | 15 | 6.08 |