Abstract | ||
---|---|---|
With the significant power of deep learning architectures, researchers have made much progress on super-resolution in the past few years. However, due to low representational ability of feature maps extracted from nature scene images, directly applying deep learning architectures for super-resolution could result in poor visual effects. Essentially, unique characteristics like low-frequency information should be emphasized for better shape reconstruction, other than treated equally across different patches and channels. To ease this problem, we propose a lightweight context-aware deep residual network named as CASR network, which appropriately encodes channel and spatial attention information to construct context-aware feature map for single-image super-resolution. We firstly design a task-specified inception block with a novel structure of astrous filters and specially chosen kernel size to extract multi-level information from low-resolution images. Then, a Dual-Attention ResNet module is applied to capture context information by dually connecting spatial and channel attention schemes. With high representational ability of context-aware feature map, CASR can accurately and efficiently generate high-resolution images. Experiments on several popular datasets show the proposed method has achieved better visual improvements and superior efficiencies than most of the existing studies. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/s00521-019-04609-8 | NEURAL COMPUTING & APPLICATIONS |
Keywords | DocType | Volume |
Context-aware residual network,Channel and spatial attention scheme,Inception block,Single-image super-resolution | Journal | 32.0 |
Issue | ISSN | Citations |
SP18.0 | 0941-0643 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yirui Wu | 1 | 13 | 7.14 |
Xiaozhong Ji | 2 | 3 | 2.06 |
Wanting Ji | 3 | 3 | 2.76 |
Yan Tian | 4 | 47 | 8.52 |
Helen Zhou | 5 | 2 | 1.10 |