Beyond Single Reference for Training: Underwater Image Enhancement via Comparative Learning

• Published in: IEEE transactions on circuits and systems for video technology Vol. 33; no. 6; pp. 2561 - 2576
• Main Authors: Li, Kunqian, Wu, Li, Qi, Qi, Liu, Wenjie, Gao, Xiang, Zhou, Liqin, Song, Dalei
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: blind image quality assessment; comparative learning; convolutional neural network; Deep learning; Electromagnetic absorption; Generators; Image degradation; Image enhancement; Oceans; Semi-supervised learning; Task analysis; Training; Underwater; Underwater image enhancement; Visualization

Due to the wavelength-dependent light absorption and scattering, the raw underwater images are usually inevitably degraded. Underwater image enhancement (UIE) is of great importance for underwater observation and operation. Data-driven methods, such as deep learning-based UIE approaches, tend to be...