Beyond Aesthetics: Quantifying Information Loss in Turbid Scenes
For underwater computer vision researchers, this work provides a real-world benchmark and a reliable metric to quantify information loss in turbid scenes, addressing a gap in synthetic data reliance.
The authors introduce the Turbid Underwater Baseline (TUB) dataset of 1,320 real turbid images with 16,000+ segmentation masks and propose PCD, a contrast-invariant metric based on phase congruency, which correlates strongly with instance segmentation performance, unlike existing metrics.
Visibility in underwater environments degrades rapidly under turbid conditions, yet the effects on computer-vision models remain unclear. This issue is compounded by reliance on synthetic turbidity datasets, which may misrepresent real-world information loss. To address this gap, we introduce the Turbid Underwater Baseline (TUB) dataset, comprising 1,320 images captured under extreme turbidity and over 16,000 high-confidence ground-truth segmentation masks. We additionally propose PCD, a metric derived from phase congruency maps that is invariant to contrast and aims to capture the loss of structural information in real turbidity. We show that PCD correlates strongly with the performance of instance segmentation models on both real and synthetic turbid images, whereas common metrics in the field show weak to no correlation at all. The dataset and relevant code can be found on the project page: https://vap.aau.dk/pcd