Tutorials
Learning Perceptual Representations for Gaming NR-VQA with Multi-Task FR Signals
arXiv:2602.11903v3 Announce Type: replace-cross Abstract: No-reference video quality assessment (NR-VQA) for gaming videos is challenging due to limited human-rated datasets and unique content charact
arXiv:2602.11903v3 Announce Type: replace-cross Abstract: 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.
Related
- Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency
- GT-SVJ: Generative-Transformer-Based Self-Supervised Video Judge For Efficient Video Reward Modeling
- Focus on What Matters: Constraining Spatial-Temporal Attention via Action-Units for Noise-Resilient AQA
Source: arXiv cs.CV | 2026-08-17