Using an adapted Stable Diffusion model as a spatial feature extractor with a Mamba temporal coherence module, DiffVQA reports top SRCC and PLCC scores on KoNViD-1k, LIVE-VQC, YouTube-UGC, LSVQ, and KVQ, with improved cross-dataset generalization.
Konvid-150k: A dataset for no-reference video qual- ity assessment of videos in-the-wild
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DiffVQA: Video Quality Assessment Using Diffusion Feature Extractor
Using an adapted Stable Diffusion model as a spatial feature extractor with a Mamba temporal coherence module, DiffVQA reports top SRCC and PLCC scores on KoNViD-1k, LIVE-VQC, YouTube-UGC, LSVQ, and KVQ, with improved cross-dataset generalization.