Learning Perceptual Representations for Gaming NR-VQA with Multi-Task FR Signals
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911456471023616 |
|---|---|
| author | Chen, Yu-Chih Wang, Michael Wen, Chieh-Dun Ma, Kai-Siang Saha, Avinab Chen, Li-Heng Bovik, Alan |
| author_facet | Chen, Yu-Chih Wang, Michael Wen, Chieh-Dun Ma, Kai-Siang Saha, Avinab Chen, Li-Heng Bovik, Alan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_11903 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning Perceptual Representations for Gaming NR-VQA with Multi-Task FR Signals Chen, Yu-Chih Wang, Michael Wen, Chieh-Dun Ma, Kai-Siang Saha, Avinab Chen, Li-Heng Bovik, Alan Image and Video Processing Computer Vision and Pattern Recognition Multimedia 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. |
| title | Learning Perceptual Representations for Gaming NR-VQA with Multi-Task FR Signals |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2602.11903 |