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 metrics as supervisory signals to learn perceptually meaningful features without human labels for pretraining. By jointly optimizing multiple full-reference (FR) objectives with adaptive task weighting, our approach learns shared representations that transfer effectively to NR-VQA. Experiments on gaming video datasets show MTL-VQA achieves performance competitive with state-of-the-art NR-VQA methods across both MOS-supervised and label-efficient/self-supervised settings.

翻译：针对游戏视频的无参考视频质量评估（NR-VQA）具有挑战性，这主要源于人工评分数据集的稀缺以及游戏内容特有的快速运动、风格化图形和压缩伪影等特征。本文提出MTL-VQA，一种多任务学习框架，该框架利用全参考指标作为监督信号，在无需人工标注的预训练过程中学习具有感知意义的特征。通过结合自适应任务加权机制联合优化多个全参考（FR）目标，我们的方法能够学习到可有效迁移至NR-VQA任务的共享表征。在游戏视频数据集上的实验表明，无论是在MOS监督还是标签高效/自监督设置下，MTL-VQA均能达到与当前最先进NR-VQA方法相竞争的性能。