SOTAVerified

Video Quality Assessment

Video Quality Assessment is a computer vision task aiming to mimic video-based human subjective perception. The goal is to produce a mos score, where higher score indicates better perceptual quality. Some well-known benchmarks for this task are KoNViD-1k, LIVE-VQC, YouTube-UGC and LSVQ. SROCC/PLCC/RMSE are usually used to evaluate the performance of different models.

Papers

Showing 110 of 216 papers

TitleStatusHype
Bridging Video Quality Scoring and Justification via Large Multimodal Models0
EyeSim-VQA: A Free-Energy-Guided Eye Simulation Framework for Video Quality Assessment0
TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs0
NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and ResultsCode0
CP-LLM: Context and Pixel Aware Large Language Model for Video Quality Assessment0
Semantically-Aware Game Image Quality Assessment0
Breaking Annotation Barriers: Generalized Video Quality Assessment via Ranking-based Self-SupervisionCode0
DiffVQA: Video Quality Assessment Using Diffusion Feature Extractor0
NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study0
NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and ResultsCode1
Show:102550
← PrevPage 1 of 22Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DOVER (end-to-end)PLCC0.87Unverified
2ReLaX-VQA (finetuned on YouTube-UGC)PLCC0.87Unverified
3DOVER (head-only)PLCC0.86Unverified
4FasterVQA (fine-tuned)PLCC0.86Unverified
5SimpleVQAPLCC0.86Unverified
6FAST-VQA (finetuned on YouTube-UGC)PLCC0.85Unverified
7HVS-5MPLCC0.85Unverified
8ReLaX-VQA (trained on LSVQ only)PLCC0.84Unverified
9CONVIQTPLCC0.82Unverified
10ReLaX-VQAPLCC0.82Unverified