AI RESEARCH
Cross-Domain Underwater Image Enhancement Guided by No-Reference Image Quality Assessment: A Transfer Learning Approach
arXiv CS.CV
•
ArXi:2503.17937v3 Announce Type: replace 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