SpatioTemporal Feature Integration and Model Fusion for Full Reference Video Quality Assessment
This work addresses the problem of efficient video quality assessment for streaming services like Netflix, but it is incremental as it builds upon the existing VMAF framework.
The authors tackled the challenge of balancing high performance and computational efficiency in video quality assessment by proposing two improvements to the VMAF framework, SpatioTemporal VMAF and Ensemble VMAF, which incorporate efficient temporal features and achieve competitive results on a large subjective database.
Perceptual video quality assessment models are either frame-based or video-based, i.e., they apply spatiotemporal filtering or motion estimation to capture temporal video distortions. Despite their good performance on video quality databases, video-based approaches are time-consuming and harder to efficiently deploy. To balance between high performance and computational efficiency, Netflix developed the Video Multi-method Assessment Fusion (VMAF) framework, which integrates multiple quality-aware features to predict video quality. Nevertheless, this fusion framework does not fully exploit temporal video quality measurements which are relevant to temporal video distortions. To this end, we propose two improvements to the VMAF framework: SpatioTemporal VMAF and Ensemble VMAF. Both algorithms exploit efficient temporal video features which are fed into a single or multiple regression models. To train our models, we designed a large subjective database and evaluated the proposed models against state-of-the-art approaches. The compared algorithms will be made available as part of the open source package in https://github.com/Netflix/vmaf.