4.6 Article

Underwater Image Enhancement Based on Zero-Reference Deep Network

期刊

IEEE JOURNAL OF OCEANIC ENGINEERING
卷 48, 期 3, 页码 903-924

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JOE.2023.3245686

关键词

Image color analysis; Image enhancement; Attenuation; Image restoration; Data models; Task analysis; Scattering; Deep network; image enhancement; Index Terms; underwater image; zero reference

向作者/读者索取更多资源

A novel Zero-Reference Deep Network for Underwater Image Enhancement is proposed in this paper, which transforms the enhancement of an underwater image into a specific parameter map estimation by using a deep network. The method utilizes a lightweight deep network to estimate the dynamic adjustment parameters of the underwater curve model and adjusts the dynamic range of the given image pixels accordingly. The significant contribution of the proposed method is zero reference, as it does not require any paired or unpaired reference data for training.
Due to underwater light absorption and scattering, underwater images usually suffer from severe color attenuation and contrast reduction. Most mainstream underwater image processing methods based on deep learning require a large amount of underwater paired training data, leading to a complex network structure, longer training time, and higher computational cost. To address this problem, a novel Zero-Reference Deep Network for Underwater Image Enhancement (Zero-UIE) is proposed in this paper, which transforms the enhancement of an underwater image into a specific parameter map estimation by using a deep network. The underwater curve model based on the classical haze image formation principle is specially designed to remove underwater color dispersion and cast. A lightweight deep network is designed to estimate the dynamic adjustment parameters of the underwater curve model, and then adjust the dynamic range of the given image pixels according to the model. A set of non-reference loss functions are designed according to the characteristics of underwater images, which can implicitly drive the network learning. In addition, adaptive color compensation can be optionally used as the pre-processing step to further improve the robustness and visual performance. The significant contribution of the proposed method is zero reference, i.e., it does not require any paired or unpaired reference data for training. Extensive experiments on various benchmarks demonstrate that the proposed method is superior to state-of-the-art methods subjectively and objectively, which is competitive and applicable to diverse underwater conditions. Most importantly, it is an innovative exploration of zero reference for underwater image enhancement.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据