Modular Blind Video Quality Assessment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916185663078400 |
|---|---|
| author | Wen, Wen Li, Mu Zhang, Yabin Liao, Yiting Li, Junlin Zhang, Li Ma, Kede |
| author_facet | Wen, Wen Li, Mu Zhang, Yabin Liao, Yiting Li, Junlin Zhang, Li Ma, Kede |
| contents | Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services. Contemporary deep learning-based models primarily analyze video content in its aggressively subsampled format, while being blind to the impact of the actual spatial resolution and frame rate on video quality. In this paper, we propose a modular BVQA model and a method of training it to improve its modularity. Our model comprises a base quality predictor, a spatial rectifier, and a temporal rectifier, responding to the visual content and distortion, spatial resolution, and frame rate changes on video quality, respectively. During training, spatial and temporal rectifiers are dropped out with some probabilities to render the base quality predictor a standalone BVQA model, which should work better with the rectifiers. Extensive experiments on both professionally-generated content and user-generated content video databases show that our quality model achieves superior or comparable performance to current methods. Additionally, the modularity of our model offers an opportunity to analyze existing video quality databases in terms of their spatial and temporal complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_19276 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Modular Blind Video Quality Assessment Wen, Wen Li, Mu Zhang, Yabin Liao, Yiting Li, Junlin Zhang, Li Ma, Kede Image and Video Processing Computer Vision and Pattern Recognition Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services. Contemporary deep learning-based models primarily analyze video content in its aggressively subsampled format, while being blind to the impact of the actual spatial resolution and frame rate on video quality. In this paper, we propose a modular BVQA model and a method of training it to improve its modularity. Our model comprises a base quality predictor, a spatial rectifier, and a temporal rectifier, responding to the visual content and distortion, spatial resolution, and frame rate changes on video quality, respectively. During training, spatial and temporal rectifiers are dropped out with some probabilities to render the base quality predictor a standalone BVQA model, which should work better with the rectifiers. Extensive experiments on both professionally-generated content and user-generated content video databases show that our quality model achieves superior or comparable performance to current methods. Additionally, the modularity of our model offers an opportunity to analyze existing video quality databases in terms of their spatial and temporal complexity. |
| title | Modular Blind Video Quality Assessment |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.19276 |