Cross-Domain Underwater Image Enhancement Guided by No-Reference Image Quality Assessment: A Transfer Learning Approach
This work addresses underwater image enhancement for applications like marine research, but it is incremental as it builds on existing transfer learning and quality assessment techniques.
The paper tackled the problem of underwater image enhancement by addressing domain discrepancy and dataset scarcity, proposing a transfer learning model that uses no-reference image quality assessment to guide cross-domain enhancement, resulting in significant outperformance over state-of-the-art methods on benchmark datasets.
Single underwater image enhancement (UIE) is a challenging ill-posed problem, but its development is hindered by two major issues: (1) The labels in underwater reference datasets are pseudo labels, relying on these pseudo ground truths in supervised learning leads to domain discrepancy. (2) Underwater reference datasets are scarce, making training on such small datasets prone to overfitting and distribution shift. To address these challenges, we propose Trans-UIE, a transfer learning-based UIE model that captures the fundamental paradigms of UIE through pretraining and utilizes a dataset composed of both reference and non-reference datasets for fine-tuning. However, fine-tuning the model using only reconstruction loss may introduce confirmation bias. To mitigate this, our method leverages no-reference image quality assessment (NR-IQA) metrics from above-water scenes to guide the transfer learning process across domains while generating enhanced images with the style of the above-water image domain. Additionally, to reduce the risk of overfitting during the pretraining stage, we introduce Pearson correlation loss. Experimental results on both full-reference and no-reference underwater benchmark datasets demonstrate that Trans-UIE significantly outperforms state-of-the-art methods.