Full-reference Video Quality Assessment for User Generated Content Transcoding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913411172925440 |
|---|---|
| author | Qi, Zihao Feng, Chen Danier, Duolikun Zhang, Fan Xu, Xiaozhong Liu, Shan Bull, David |
| author_facet | Qi, Zihao Feng, Chen Danier, Duolikun Zhang, Fan Xu, Xiaozhong Liu, Shan Bull, David |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_12317 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Full-reference Video Quality Assessment for User Generated Content Transcoding Qi, Zihao Feng, Chen Danier, Duolikun Zhang, Fan Xu, Xiaozhong Liu, Shan Bull, David Image and Video Processing 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. |
| title | Full-reference Video Quality Assessment for User Generated Content Transcoding |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2312.12317 |