用全参考指标指导无参考游戏视频质量评估，无需人工评分即可学出感知有效特征。
Learning Perceptual Representations for Gaming NR-VQA with Multi-Task FR Signals
- 多任务学习融合多个全参考指标作为监督信号训练模型
- 在游戏视频数据集上性能媲美主流方法，支持有标注和少标注场景
- 适合缺乏人工评分的游戏视频质量评估研究者使用
针对游戏视频的无参考视频质量评估（NR-VQA）因缺乏人类评分数据集且内容具有快速运动、风格化画面和压缩伪影等特性而极具挑战。本文提出MTL-VQA，一种多任务学习框架，利用全参考（FR）质量指标作为监督信号，在预训练阶段无需人工标签即可学习感知有意义的特征。通过联合优化多个互补的代理FR目标并采用自适应任务加权，该方法学习到可有效迁移到下游NR-VQA任务的共享表示。在游戏视频数据集上的实验表明，MTL-VQA在均值意见分数监督、标签高效或自监督设置下均达到与当前最优方法相当的性能。
原文摘要 · Abstract (English)
No-reference video quality assessment (NR-VQA) for gaming videos is challenging due to limited human-rated datasets and unique content characteristics including fast motion, stylized graphics, and compression artifacts. We present MTL-VQA, a multi-task learning framework that uses full-reference (FR) quality metrics as supervisory signals to learn perceptually meaningful features without human labels during pretraining. By jointly optimizing multiple complementary proxy FR objectives with adaptive task weighting, our approach learns shared representations that transfer effectively to downstream NR-VQA. Experiments on gaming video datasets show that MTL-VQA achieves competitive performance against state-of-the-art methods in both mean opinion score-supervised and label-efficient or self-supervised settings.
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。