HCLR-Net: Hybrid Contrastive Learning Regularization with Locally Randomized Perturbation for Underwater Image Enhancement

Underwater image enhancement presents a significant challenge due to the complex and diverse underwater environments that result in severe degradation phenomena such as light absorption, scattering, and color distortion. More importantly, obtaining paired training data for these scenarios is a challenging task, which further hinders the generalization performance of enhancement models. To address these issues, we propose a novel approach, the Hybrid Contrastive Learning Regularization (HCLR-Net). Our method is built upon a distinctive hybrid contrastive learning regularization strategy that incorporates a unique methodology for constructing negative samples. This approach enables the network to develop a more…

• NN
  National Natural Science Foundation of China

  Awards: 62271277, 62301105, 2022J081
• HK
  Hong Kong Polytechnic University
• NS
  Natural Science Foundation of Ningbo

  Award: 2022J081
• FR
  Fundamental Research Funds for the Central Universities

  Awards: 3132019354, 3132019205
• NS
  Natural Science Foundation of Zhejiang Province

  Award: LR22F020002