JEVQA - 基于元数据、比特流和像素特征及通用决策模型的视频质量评估

中文摘要 AI 辅助

用于视频质量预测的仪器质量模型通常针对一组固定的编解码器或其他输入特征进行训练，并且每个新的输入变量都需要重新训练。新颖的通用决策模型可以在无需特定任务训练的情况下回答问题，但尚不清楚它们能否判断视频质量。我们评估了Jev，一个商业化的“系统一”模型，该模型在提供的答案尺度上返回概率分布，作为零样本视频质量模型。我们将由此产生的方法称为JEVQA。在第一项研究中，针对22个来源的1,936个AV1、H.264、HEVC和VP9编码，以VMAF作为地面真值进行评分，仅使用编码元数据，JEVQA达到了0.737的皮尔逊相关系数，与标准化的ITU-T P.1204.1模型（0.733）相当。向模型提供比特流数据将准确率提高到0.797，而结合基于像素和比特流的特征则将其提高到0.824。仅使用像素的变体在我们的测试中失败。在第二项研究中，使用AVT-VQDB-UHD-1数据库中的H.264、HEVC和VP9编码，仅元数据模型与MOS的相关性达到0.879，接近P.1204.1（0.898）。比特流统计在那里没有帮助。我们的结果表明，在相同特征上训练的模型在两项研究中仍明显领先，但零样本分类器显示出潜力。

英文摘要

Instrumental quality models for video quality prediction are usually trained for a fixed set of codecs or other input features, and every new input variable requires retraining. Novel, general-purpose decision models can answer questions without task-specific training, but it is unclear whether they can judge video quality. We evaluate Jev, a commercial ``System One'' model that returns probability distributions over a provided answer scale, as a zero-shot video quality model. We call the resulting method JEVQA. In a first study on 1,936 AV1, H.264, HEVC, and VP9 encodes of 22 sources, scored against VMAF as ground truth, using encoding metadata only, JEVQA reached a Pearson correlation of 0.737, on par with the standardized ITU-T P.1204.1 model (0.733). Giving the model bitstream data raised the accuracy to 0.797, and combined pixel-based and bitstream features raised it to 0.824. A pixel-only variant failed in our tests. In a second study, using H.264, HEVC, and VP9 encodes in the AVT-VQDB-UHD-1 database, the metadata-only model reached a correlation of 0.879 with MOS, close to P.1204.1 (0.898). Bitstream statistics did not help there. Our results show that trained models on the same features remain clearly ahead in both studies, but that zero-shot classifiers are promising.

发表机构

• AVEQ GmbH（AVEQ有限公司）

机构由 AI 辅助整理，请以论文原文为准。