arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.07489cs.CV
收藏

MRET:用于视频质量评估的多分辨率Transformer

MRET: Multi-resolution Transformer for Video Quality Assessment

Google Research(谷歌研究院);Google(谷歌)

Junjie Ke, Tianhao Zhang, Yilin Wang, Peyman Milanfar, Feng Yang

摘要:

用户生成内容(UGC)的无参考视频质量评估(NR-VQA)对于理解和改善视觉体验至关重要。与视频识别任务不同,VQA任务对输入分辨率的变化很敏感。由于现在大量的UGC视频都是720 p或更高,传统NR-VQA方法中使用的固定且相对较小的输入导致许多视频丢失高频细节。在本文中,我们提出了一种新的基于transformer的NR-VQA框架,保留了高分辨率的质量信息。通过多分辨率输入表示和一种新的多分辨率补丁采样机制,我们的方法可以全面地查看全局视频组成和局部高分辨率细节。所提出的方法可以有效地聚合质量信息在不同粒度的空间和时间维度,使模型的鲁棒性输入分辨率的变化。我们的方法在大规模UGC VQA数据集LSVQ和LSVQ-1080 p以及KoNViD-1 k和LIVE-VQC上实现了最先进的性能,无需微调。

英文摘要:

No-reference video quality assessment (NR-VQA) for user generated content (UGC) is crucial for understanding and improving visual experience. Unlike video recognition tasks, VQA tasks are sensitive to changes in input resolution. Since large amounts of UGC videos nowadays are 720p or above, the fixed and relatively small input used in conventional NR-VQA methods results in missing high-frequency details for many videos. In this paper, we propose a novel Transformer-based NR-VQA framework that preserves the high-resolution quality information. With the multi-resolution input representation and a novel multi-resolution patch sampling mechanism, our method enables a comprehensive view of both the global video composition and local high-resolution details. The proposed approach can effectively aggregate quality information across different granularities in spatial and temporal dimensions, making the model robust to input resolution variations. Our method achieves state-of-the-art performance on large-scale UGC VQA datasets LSVQ and LSVQ-1080p, and on KoNViD-1k and LIVE-VQC without fine-tuning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑