An Underwater Image Enhancement Method for a Preprocessing Framework Based on Generative Adversarial Network
Open Access
Abstract
This paper presents an efficient underwater image enhancement method, named ECO-GAN, to address the challenges of color distortion, low contrast, and motion blur in underwater robot photography. The proposed method is built upon a preprocessing framework using a generative adversarial network. ECO-GAN incorporates a convolutional neural network that specifically targets three underwater issues: motion blur, low brightness, and color deviation. To optimize computation and inference speed, an encoder is employed to extract features, whereas different enhancement tasks are handled by dedicated decoders. Moreover, ECO-GAN employs cross-stage fusion modules between the decoders to strengthen the connection and enhance the quality of output images. The model is trained using supervised learning with paired datasets, enabling blind image enhancement without additional physical knowledge or prior information. Experimental results demonstrate that ECO-GAN effectively achieves denoising, deblurring, and color deviation removal simultaneously. Compared with methods relying on individual modules or simple combinations of multiple modules, our proposed method achieves superior underwater image enhancement and offers the flexibility for expansion into multiple underwater image enhancement functions.Keywords
Funding Information
- National Key Research and Development Project of China (2022YFC2803600, 2022C03027, 2022C01144, LGF21E090004, LGF22E090006, 202203B35)
- Key Research and Development Program of Zhejiang Province (2022YFC2803600, 2022C03027, 2022C01144, LGF21E090004, LGF22E090006, 202203B35)
- Public Welfare Technology Research Project of Zhejiang Province (2022YFC2803600, 2022C03027, 2022C01144, LGF21E090004, LGF22E090006, 202203B35)
- Hangzhou science and technology development plan project (2022YFC2803600, 2022C03027, 2022C01144, LGF21E090004, LGF22E090006, 202203B35)
- Zhejiang Provincial Key Lab of Equipment Electronics (2022YFC2803600, 2022C03027, 2022C01144, LGF21E090004, LGF22E090006, 202203B35)
This publication has 28 references indexed in Scilit:
- Emerging From Water: Underwater Image Color Correction Based on Weakly Supervised Color TransferIEEE Signal Processing Letters, 2018
- Two-step approach for single underwater image enhancement2017
- Color Balance and Fusion for Underwater Image EnhancementIEEE Transactions on Image Processing, 2017
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater ImagesIEEE Robotics and Automation Letters, 2017
- Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution PriorIEEE Transactions on Image Processing, 2016
- Underwater image restoration based on minimum information loss principle and optical properties of underwater imaging2016
- Underwater Depth Estimation and Image Restoration Based on Single ImagesIEEE Computer Graphics and Applications, 2016
- A retinex-based enhancing approach for single underwater image2014
- Initial results in underwater single image dehazing2010