Is there a relationship between Mean Opinion Score (MOS) and Just Noticeable Difference (JND)?

2026-02-18

AI Summary

This study addresses the unclear mapping between Mean Opinion Score (MOS) and Just Noticeable Difference (JND) in high-fidelity video scenarios, which hinders precise subjective quality assessment and perceptually optimized bitrate ladder design. For the first time, it systematically investigates the relationship between MOS and the 75% Satisfaction User Ratio (SUR) points corresponding to the first and second JNDs in the high-quality regime. Leveraging Degradation Category Rating (DCR) subjective experiments, existing JND datasets, statistical significance testing, confidence interval estimation, and cross-validation, the work reveals that MOS values at JND points broadly align with theoretical expectations—e.g., MOS ≈ 4.75 for the first JND. However, reverse mapping from MOS to JND exhibits uncertainty due to overlapping confidence intervals, and small-sample DCR experiments struggle to reliably detect statistically significant differences between reference and JND-level videos.

Technology Category

• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction
• Computer Vision: Video Understanding & Activity Analysis
• Knowledge Representation and Reasoning: Preferences

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Evaluating perceived video quality is essential for ensuring high Quality of Experience (QoE) in modern streaming applications. While existing subjective datasets and Video Quality Metrics (VQMs) cover a broad quality range, many practical use cases especially for premium users focus on high quality scenarios requiring finer granularity. Just Noticeable Difference (JND) has emerged as a key concept for modeling perceptual thresholds in these high end regions and plays an important role in perceptual bitrate ladder construction. However, the relationship between JND and the more widely used Mean Opinion Score (MOS) remains unclear. In this paper, we conduct a Degradation Category Rating (DCR) subjective study based on an existing JND dataset to examine how MOS corresponds to the 75% Satisfied User Ratio (SUR) points of the 1st and 2nd JNDs. We find that while MOS values at JND points generally align with theoretical expectations (e.g., 4.75 for the 75% SUR of the 1st JND), the reverse mapping from MOS to JND is ambiguous due to overlapping confidence intervals across PVS indices. Statistical significance analysis further shows that DCR studies with limited participants may not detect meaningful differences between reference and JND videos.

Problem

• Mean Opinion Score
• Just Noticeable Difference
• Video Quality
• Quality of Experience
• Perceptual Threshold

Innovation

• Just Noticeable Difference (JND)
• Mean Opinion Score (MOS)
• Subjective Video Quality
• Satisfied User Ratio (SUR)
• Degradation Category Rating (DCR)