.png){kind=icon}
Return
Multi-attention augmented network for single image super-resolution
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2021.108349.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
How to improve the representational power of visual features extracted by deep convolutional neural networks is of crucial importance for high-quality image super-resolution. To address this issue, we propose a multi-attention augmented network, which mainly consists of content-, orientation-and position-aware modules. Specifically, we develop an attention augmented U-net structure to form the content-aware module in order to learn and combine multi-scale informative features within a large receptive field. To better reconstruct image details in different directions, we design a set of pre-defined sparse kernels to construct the orientation-aware module, which can extract more representative multi-orientation features and enhance the discriminative capacity in stacked convolutional stages. Then these extracted features are adaptively fused through channel attention mechanism. In upscale stage, the position-aware module adopts a novel self-attention to reweight the element-wise value of final low-resolution feature maps, for further suppressing the possible artifacts. Experimental results demonstrate that our method obtains better reconstruction accuracy and perceptual quality against state-of-the-art methods. (c) 2021 Elsevier Ltd. All rights reserved.
Keywords:
Super-resolution
Multi-scale U-net
pre-defined sparse kernels
Attention mechanism
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
ShareSaveBlue Sky Protection Campaign: Assessing the Role of Digital Technology in Reducing Air Pollution.png)
Systems
OAAI
SystemsIF0
OAAIShareSaveShareSaveShareSaveSimultaneous color-depth super-resolution with conditional generative adversarial networksPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSave
View more