Fine-Grained HDR Image Quality Assessment From Noticeably Distorted to Very High Fidelity

2025-06-14

AI Summary

HDR/WCG technologies enhance visual quality but exacerbate bandwidth and compression challenges—particularly in the high-fidelity regime (between visible distortion and perceptually lossless thresholds), where minute perceptual differences demand precise evaluation. Yet, existing subjective datasets for this regime are severely lacking. To address this, we introduce AIC-HDR2025, the first benchmark dedicated to high-fidelity HDR image quality assessment. It features the first standardized HDR high-fidelity subjective dataset and proposes the enhanced AIC-3 triplet protocol, integrating both plain and boosted triplet comparisons. Conducted across four laboratories via large-scale crowdsourcing, our study generates diverse HDR distortions using multiple encoders and bitrates. We collect 34,560 high-quality subjective scores, achieving a narrow mean 95% confidence interval width of just 0.27 JND. Experiments expose fundamental correlation bottlenecks of state-of-the-art objective metrics in this regime. All data and protocols are publicly released.

Technology Category

• Computer Vision: Image and Video Retrieval
• Humans and AI: Crowd Sourcing and Human Computation
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

High dynamic range (HDR) and wide color gamut (WCG) technologies significantly improve color reproduction compared to standard dynamic range (SDR) and standard color gamuts, resulting in more accurate, richer, and more immersive images. However, HDR increases data demands, posing challenges for bandwidth efficiency and compression techniques. Advances in compression and display technologies require more precise image quality assessment, particularly in the high-fidelity range where perceptual differences are subtle. To address this gap, we introduce AIC-HDR2025, the first such HDR dataset, comprising 100 test images generated from five HDR sources, each compressed using four codecs at five compression levels. It covers the high-fidelity range, from visible distortions to compression levels below the visually lossless threshold. A subjective study was conducted using the JPEG AIC-3 test methodology, combining plain and boosted triplet comparisons. In total, 34,560 ratings were collected from 151 participants across four fully controlled labs. The results confirm that AIC-3 enables precise HDR quality estimation, with 95% confidence intervals averaging a width of 0.27 at 1 JND. In addition, several recently proposed objective metrics were evaluated based on their correlation with subjective ratings. The dataset is publicly available.

Problem

• Assessing HDR image quality from noticeable distortions to high fidelity
• Addressing challenges in HDR compression and bandwidth efficiency
• Evaluating perceptual differences in high-fidelity HDR images

Innovation

• First HDR dataset AIC-HDR2025 with 100 test images
• JPEG AIC-3 methodology for precise quality estimation
• Evaluated multiple objective metrics against subjective ratings