Research Article
Adaptive Channel Attention-Based Deformable Generative Adversarial Network for Underwater Image Enhancement
@INPROCEEDINGS{10.1007/978-3-031-34899-0_2, author={Tingkai Chen and Ning Wang and Xiangjun Kong and Yanzheng Chen}, title={Adaptive Channel Attention-Based Deformable Generative Adversarial Network for Underwater Image Enhancement}, proceedings={Sensor Systems and Software. 13th EAI International Conference, S-Cube 2022, Dalian, China, December 7-9, 2022, Proceedings}, proceedings_a={S-CUBE}, year={2023}, month={6}, keywords={Underwater image enhancement Generative adversarial network Adaptive channel attention Deformable convolution network}, doi={10.1007/978-3-031-34899-0_2} }- Tingkai Chen
Ning Wang
Xiangjun Kong
Yanzheng Chen
Year: 2023
Adaptive Channel Attention-Based Deformable Generative Adversarial Network for Underwater Image Enhancement
S-CUBE
Springer
DOI: 10.1007/978-3-031-34899-0_2
Abstract
In this paper, to effectively strengthen quality of underwater image enhancement from both channel and spatial viewpoints, an adaptive channel attention-based deformable generative adversarial networks (ACADGAN) framework is established. Main contributions are as follows. 1) By virtue of multi-branch convolution architecture with dilated convolution mechanism, the adaptive channel attention (ACA) is devised, such that channel weight can be adaptively recalibrated, and thereby significantly contributing to preserving content features from channel viewpoint. 2) By augmenting offset position of sampling point with respect to convolution kernel, the deformable convolution network (DCN) is created, such that detailed information of underwater image can be dramatically retained from spatial aspect. 3) The ACADGAN scheme is eventually proposed by integrating ACA and DCN modules with a deep generative adversarial network. Comprehensive experiments demonstrate the remarkable effectiveness and superiority of the developed ACADGAN scheme.
