Full-reference Video Quality Assessment for User Generated Content Transcoding
arXiv:2312.12317 · doi:10.1109/PCS60826.2024.10566416
Abstract
Unlike video coding for professional content, the delivery pipeline of User Generated Content (UGC) involves transcoding where unpristine reference content needs to be compressed repeatedly. In this work, we observe that existing full-/no-reference quality metrics fail to accurately predict the perceptual quality difference between transcoded UGC content and the corresponding unpristine references. Therefore, they are unsuited for guiding the rate-distortion optimisation process in the transcoding process. In this context, we propose a bespoke full-reference deep video quality metric for UGC transcoding. The proposed method features a transcoding-specific weakly supervised training strategy employing a quality ranking-based Siamese structure. The proposed method is evaluated on the YouTube-UGC VP9 subset and the LIVE-Wild database, demonstrating state-of-the-art performance compared to existing VQA methods.
arXiv comment5 pages, 4 figures
References in corpus (7)
- UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
- Large-Scale Study of Perceptual Video Quality
- YouTube UGC Dataset for Video Compression Research
- A Deep Learning based No-reference Quality Assessment Model for UGC Videos
- BVI-DVC: A Training Database for Deep Video Compression
- Predicting the Quality of Compressed Videos with Pre-Existing Distortions
- RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training