What question did this study set out to answer?

This research aims to establish a reliable evaluation framework for underwater image enhancement by combining subjective and objective quality assessments.

June 4, 2026Open Access

Towards Reliable Evaluation of Underwater Image Enhancement Using Subjective and Objective Analysis

Puntos clave

This research aims to establish a reliable evaluation framework for underwater image enhancement by combining subjective and objective quality assessments.
Conducted a controlled, laboratory-based subjective study using the ITU-R absolute category rating protocol.
Evaluated 132 images from the UIEBD dataset and 120 images from the EUVP dataset, including images enhanced by four deep learning models.
Analyzed correlation of results from subjective evaluations against objective metrics, focusing on new no-reference quality assessment models.
Modern learning-based no-reference image quality assessment models show higher correlation with subjective mean opinion scores compared to traditional measures.
TOPIQ_NR achieves a Spearman correlation of 0.80 on UIEBD dataset, while LIQE reaches 0.87 on the EUVP dataset.
Conventional measures like UIQM and UCIQE demonstrated weaker alignment with human perception, indicating the need for adopting learning-based metrics.

Resumen

This paper presents a systematic evaluation framework for underwater image enhancement (UIE), focusing on reliable quality assessment for vision applications in challenging underwater environments. The framework jointly analyzes subjective visual quality and objective image quality assessment measures. A controlled, laboratory-based subjective study following the ITU-R absolute category rating protocol is conducted on two datasets: UIEBD (with and without quasi-reference images) and the EUVP validation subset. A total of 132 images from UIEBD and 120 images from EUVP are evaluated, including enhanced images from four recent deep learning-based UIE models (CCL-Net, HUPE, GuidedHybSensUIR, and UDNet). The subjective results reveal dataset-dependent behavior of the evaluated methods, highlighting the challenges of reliable perceptual evaluation in the presence of diverse degradations and quasi-reference data. Objective analysis shows that modern learning-based, no-reference image quality assessment (NR-IQA) models exhibit higher correlation with subjective mean opinion scores than traditional underwater-specific measures. In particular, TOPIQNR achieves a Spearman correlation of 0. 80 on UIEBD and remains among the top-performing methods on EUVP, where LIQE reaches 0. 87, while widely used measures such as UIQM and UCIQE show weaker alignment with human perception. These findings support the adoption of learning-based NR-IQA measures for robust underwater vision systems.

Leer artículo completoexternamente

Me gusta

Guardar

Ver artículo completo