Blind Video Quality Assessment on Waterloo-IVC-4K
0.8398SRCCFDIM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FDIMFramework=Hybrid2026.04 | 0.8398 | 0.8472 | |
| FDIMFramework=Deep feature component2026.04 | 0.8385 | 0.8504 | |
| qstdescription=complete model (spatial + temporal rectifiers)2024.02 | 0.807 | 0.843 | |
| qsdescription=with spatial rectifier2024.02 | 0.805 | 0.844 | |
| TOPIQ2026.04 | 0.7953 | 0.8 | |
| qbdescription=base quality predictor2024.02 | 0.785 | 0.834 | |
| XPSNR2026.04 | 0.7807 | 0.7856 | |
| qtdescription=with temporal rectifier2024.02 | 0.77 | 0.832 | |
| DISTS2026.04 | 0.7134 | 0.7259 | |
| VMAF2026.04 | 0.7113 | 0.7046 | |
| LMM-PVQA (Soft Ranking Stage 3)Training data=PLVD-P1/ P2/ P3 (700k), Human Label=No, Setting=Zero-shot2025.05 | 0.67 | 0.728 | |
| RankDVQA2026.04 | 0.6501 | 0.6619 | |
| LMM-PVQA (Soft Ranking Stage 2)Training data=PLVD-P1/ P2 (600k), Human Label=No, Setting=Zero-shot2025.05 | 0.633 | 0.696 | |
| VersusQMethod Category=Reasoning or reinforcement-learning based LMM evaluators2026.05 | 0.587 | 0.67 | |
| VQAThinkerMethod Category=Reasoning or reinforcement-learning based LMM evaluators2026.05 | 0.573 | 0.624 | |
| BTURA2024.02 | 0.562 | 0.625 | |
| LMM-PVQA (Soft Ranking Stage 1)Training data=PLVD-P1 (500k), Human Label=No, Setting=Zero-shot2025.05 | 0.552 | 0.614 | |
| MS-SSIM2026.04 | 0.5198 | 0.5242 | |
| LPIPS2026.04 | 0.5098 | 0.5317 | |
| SSIM2026.04 | 0.4978 | 0.5119 | |
| LMM-PVQA (Hard Ranking)Training data=PLVD-P1 (500k), Human Label=No, Setting=Zero-shot2025.05 | 0.492 | 0.542 | |
| PSNR2026.04 | 0.4706 | 0.4844 | |
| MinimalisticVQA(IX)Training data=LSVQ [70], Human Label=Yes, Setting=Zero-shot2025.05 | 0.459 | 0.502 | |
| MinimalisticVQAMethod Category=Supervised VQA/IQA models2026.05 | 0.459 | 0.502 | |
| VQA2-ScorerMethod Category=Supervised VQA/IQA models2026.05 | 0.415 | 0.474 | |
| Q-AlignTraining data=fused [11, 17, 28, 40, 70], Human Label=Yes, Setting=Zero-shot2025.05 | 0.414 | 0.497 | |
| Q-AlignMethod Category=Supervised VQA/IQA models2026.05 | 0.414 | 0.497 | |
| SimpleVQAMethod Category=Supervised VQA/IQA models2026.05 | 0.379 | 0.425 | |
| DOVERTraining data=LSVQ [70], Human Label=Yes, Setting=Zero-shot2025.05 | 0.368 | 0.418 | |
| DOVERMethod Category=Supervised VQA/IQA models2026.05 | 0.368 | 0.418 | |
| FAST-VQATraining data=LSVQ [70], Human Label=Yes, Setting=Zero-shot2025.05 | 0.327 | 0.363 | |
| FAST-VQAMethod Category=Supervised VQA/IQA models2026.05 | 0.327 | 0.363 | |
| MinimalisticVQA(VII)Training data=LSVQ [70], Human Label=Yes, Setting=Zero-shot2025.05 | 0.275 | 0.338 | |
| VisualQuality-R1Method Category=Reasoning or reinforcement-learning based LMM evaluators2026.05 | 0.227 | 0.298 | |
| Q-InsightMethod Category=Reasoning or reinforcement-learning based LMM evaluators2026.05 | 0.218 | 0.206 | |
| STEMTraining data=None, Human Label=No, Setting=Zero-shot2025.05 | 0.184 | 0.097 | |
| STEMMethod Category=Training-free / unsupervised quality models2026.05 | 0.184 | 0.097 | |
| BRISQUE2024.02 | 0.154 | 0.248 | |
| CLIP-IQAMethod Category=Training-free / unsupervised quality models2026.05 | 0.133 | 0.213 | |
| VSFA2024.02 | 0.122 | 0.148 | |
| VIIDEOTraining data=None, Human Label=No, Setting=Zero-shot2025.05 | 0.114 | 0.078 | |
| VIIDEOMethod Category=Training-free / unsupervised quality models2026.05 | 0.114 | 0.078 | |
| NIQE2024.02 | 0.099 | 0.16 | |
| IL-NIQETraining data=None, Human Label=No, Setting=Zero-shot2025.05 | 0.079 | -0.008 | |
| NIQETraining data=None, Human Label=No, Setting=Zero-shot2025.05 | 0.048 | 0.002 | |
| NIQEMethod Category=Training-free / unsupervised quality models2026.05 | 0.048 | 0.002 |