Do Underwater Image Quality Metrics Agree with Human Perception? A Benchmark with Human Choices, Simple Edits and Generative Drift A benchmark study evaluated 73 handcrafted underwater no-reference image quality assessment (NR-IQA) metrics against human judgments to test whether the metrics agree with human perception of enhanced underwater images. The research addresses the difficulty of evaluating underwater image enhancement, where the absence of clean reference images forces reliance on no-reference metrics, and incorporates human choices, simple edits and generative drift into the comparison. Underwater image enhancement is challenging to evaluate due to the lack of clean reference images, so researchers rely on no-reference image quality assessment NR-IQA metrics. However, it remains unclear whether these metrics agree with human judgments. We evaluate 73 handcrafted underwater, learn