DIVA-VQA: Detecting Inter-frame Variations in UGC Video Quality
By: Xinyi Wang, Angeliki Katsenou, David Bull
Potential Business Impact:
Checks video quality without a reference copy.
The rapid growth of user-generated (video) content (UGC) has driven increased demand for research on no-reference (NR) perceptual video quality assessment (VQA). NR-VQA is a key component for large-scale video quality monitoring in social media and streaming applications where a pristine reference is not available. This paper proposes a novel NR-VQA model based on spatio-temporal fragmentation driven by inter-frame variations. By leveraging these inter-frame differences, the model progressively analyses quality-sensitive regions at multiple levels: frames, patches, and fragmented frames. It integrates frames, fragmented residuals, and fragmented frames aligned with residuals to effectively capture global and local information. The model extracts both 2D and 3D features in order to characterize these spatio-temporal variations. Experiments conducted on five UGC datasets and against state-of-the-art models ranked our proposed method among the top 2 in terms of average rank correlation (DIVA-VQA-L: 0.898 and DIVA-VQA-B: 0.886). The improved performance is offered at a low runtime complexity, with DIVA-VQA-B ranked top and DIVA-VQA-L third on average compared to the fastest existing NR-VQA method. Code and models are publicly available at: https://github.com/xinyiW915/DIVA-VQA.
Similar Papers
CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video
Image and Video Processing
Makes online videos look better automatically.
NovisVQ: A Streaming Convolutional Neural Network for No-Reference Opinion-Unaware Frame Quality Assessment
CV and Pattern Recognition
Checks video quality without needing perfect copies.
ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images
CV and Pattern Recognition
Makes AI better at judging photo quality.