构建首个真实场景下HDR与SDR视频质量对比数据集
HDRSDR-VQA: A Subjective Video Quality Dataset for HDR and SDR Comparative Evaluation
- 在6台电视上对960段视频做双格式对比测试
- 22000+次主观评分生成可量化差异指标
- 适合研究画质评估、自适应流媒体的学者
我们提出HDRSDR-VQA，一个大规模视频质量评估数据集，用于在真实观看条件下比较高动态范围（HDR）与标准动态范围（SDR）内容。数据集包含54个不同源视频序列生成的960段视频，每段视频均以HDR和SDR两种格式呈现，共九种失真等级。为获取可靠感知质量评分，我们组织了145名参与者在六台消费级HDR电视上完成全面主观实验，收集超过22,000次成对比较，并将其转换为刚刚可察觉差异（JOD）分数。与以往仅关注单一动态范围或评估方式受限的数据集不同，HDRSDR-VQA支持在内容级别直接比较HDR与SDR版本，有助于深入探究两种格式在何种情况下更受青睐。数据集部分已开源，可用于视频质量评估、内容自适应流媒体及感知模型开发研究。
原文摘要 · Abstract (English)
We introduce HDRSDR-VQA, a large-scale video quality assessment dataset designed to facilitate comparative analysis between High Dynamic Range (HDR) and Standard Dynamic Range (SDR) content under realistic viewing conditions. The dataset comprises 960 videos generated from 54 diverse source sequences, each presented in both HDR and SDR formats across nine distortion levels. To obtain reliable perceptual quality scores, we conducted a comprehensive subjective study involving 145 participants and six consumer-grade HDR-capable televisions. A total of over 22,000 pairwise comparisons were collected and scaled into Just-Objectionable-Difference (JOD) scores. Unlike prior datasets that focus on a single dynamic range format or use limited evaluation protocols, HDRSDR-VQA enables direct content-level comparison between HDR and SDR versions, supporting detailed investigations into when and why one format is preferred over the other. The open-sourced part of the dataset is publicly available to support further research in video quality assessment, content-adaptive streaming, and perceptual model development.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。