Browse › Computer Vision › Video Quality Assessment › MSU SR-QA Dataset
MSU SR-QA Dataset Benchmark (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.
The archive carries no text for this table; the description above is the archive's text for the task Video Quality Assessment. archive 2025-07-28
Over time archive 2025-07-28
The chart needs JavaScript; the table below carries every value.
Not inferred: SROCC, PLCC, KLCC, Type. Points are placed at the row's paper date; 48 of 60 rows carry one.
Results archive 2025-07-28
Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.
| Paper | Code | Ran Syntology | Report | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | PieAPP | 0.75215 | 0.75743 | 0.61945 | FR | – | Paper | Code | 2018 | linked, not harvested | report |
| 2 | Q-Align (IQA) | 0.75088 | 0.74116 | 0.61677 | NR | – | Paper | Code | 2023 | 2 of 2 ran · 0 unverified | report |
| 3 | Q-Align (VQA) | 0.71812 | 0.71121 | 0.58634 | NR | – | Paper | Code | 2023 | 2 of 2 ran · 0 unverified | report |
| 4 | PaQ-2-PiQ | 0.71167 | 0.70988 | 0.57753 | NR | – | Paper | Code | 2019 | linked, not harvested | report |
| 5 | DBCNN | 0.68621 | 0.63971 | 0.55139 | NR | – | Paper | Code | 2019 | 4 of 10 ran · 6 unverified | report |
| 6 | MUSIQ trained on PaQ-2-PiQ | 0.67746 | 0.66531 | 0.55312 | NR | – | Paper | Code | 2021 | 5 of 6 ran · 1 unverified | report |
| 7 | Ma-Metric | 0.67362 | 0.65357 | 0.52301 | NR | – | Paper | Code | 2016 | linked, not harvested | report |
| 8 | MANIQA | 0.66613 | 0.62733 | 0.54744 | NR | – | Paper | Code | 2022 | 2 of 9 ran · 7 unverified | report |
| 9 | ClipIQA+ ResNet50 | 0.65713 | 0.65154 | 0.52628 | NR | – | Paper | Code | 2022 | linked, not harvested | report |
| 10 | MUSIQ trained on SPAQ | 0.64927 | 0.60216 | 0.52673 | NR | – | Paper | Code | 2021 | 5 of 6 ran · 1 unverified | report |
| 11 | TOPIQ trained on SPAQ (NR) | 0.64923 | 0.60905 | 0.53140 | NR | – | Paper | Code | 2023 | 3 of 10 ran · 7 unverified | report |
| 12 | MUSIQ trained on KONIQ | 0.64589 | 0.59151 | 0.51897 | NR | – | Paper | Code | 2021 | 5 of 6 ran · 1 unverified | report |
| 13 | Linearity (Norm-in-Norm Loss) | 0.64382 | 0.62204 | 0.52172 | NR | – | Paper | Code | 2020 | 3 of 3 ran · 0 unverified | report |
| 14 | TOPIQ | 0.62715 | 0.57674 | 0.50670 | NR | – | Paper | Code | 2023 | 3 of 10 ran · 7 unverified | report |
| 15 | TReS trained on KONIQ | 0.62578 | 0.56226 | 0.49004 | NR | – | Paper | Code | 2021 | linked, not harvested | report |
| 16 | TReS | 0.62496 | 0.56277 | 0.48901 | NR | – | Paper | Code | 2021 | linked, not harvested | report |
| 17 | ClipIQA | 0.60808 | 0.58944 | 0.49417 | NR | – | Paper | Code | 2022 | linked, not harvested | report |
| 18 | AHIQ | 0.60468 | 0.62311 | 0.47674 | FR | – | – | – | not matched | report | |
| 19 | MDTVSFA | 0.60193 | 0.61821 | 0.48406 | NR | – | Paper | Code | 2020 | linked, not harvested | report |
| 20 | HyperIQA | 0.59883 | 0.55211 | 0.48466 | NR | – | Paper | Code | 2020 | linked, not harvested | report |
| 21 | TOPIQ FACE | 0.59564 | 0.58949 | 0.48428 | NR | – | Paper | Code | 2023 | 3 of 10 ran · 7 unverified | report |
| 22 | ERQA | 0.59345 | 0.60188 | 0.47785 | FR | – | Paper | Code | 2021 | linked, not harvested | report |
| 23 | TOPIQ | 0.57341 | 0.57955 | 0.46217 | FR | – | Paper | Code | 2023 | 3 of 10 ran · 7 unverified | report |
| 24 | ST-LPIPS (VGG) | 0.57336 | 0.56431 | 0.45898 | FR | – | Paper | Code | 2022 | 7 of 21 ran · 14 unverified | report |
| 25 | ClipIQA+ | 0.56875 | 0.71808 | 0.69774 | NR | – | Paper | Code | 2022 | linked, not harvested | report |
| 26 | MUSIQ trained on AVA | 0.56152 | 0.52404 | 0.44669 | NR | – | Paper | Code | 2021 | 5 of 6 ran · 1 unverified | report |
| 27 | TOPIQ trained on PIPAL | 0.55568 | 0.57564 | 0.42811 | FR | – | Paper | Code | 2023 | 3 of 10 ran · 7 unverified | report |
| 28 | LPIPS (Alex) | 0.54461 | 0.52385 | 0.43158 | FR | – | Paper | Code | 2018 | 2 of 2 ran · 0 unverified | report |
| 29 | VSFA | 0.53652 | 0.54407 | 0.43634 | NR | – | Paper | Code | 2019 | 2 of 3 ran · 1 unverified | report |
| 30 | ST-LPIPS (Alex) | 0.53473 | 0.54740 | 0.42897 | FR | – | Paper | Code | 2022 | 7 of 21 ran · 14 unverified | report |
| 31 | DISTS | 0.53346 | 0.55042 | 0.42320 | FR | – | Paper | Code | 2020 | 0 of 2 ran · 2 unverified | report |
| 32 | LPIPS (VGG) | 0.52868 | 0.52820 | 0.41471 | FR | – | Paper | Code | 2018 | 2 of 2 ran · 0 unverified | report |
| 33 | PI | 0.52319 | 0.53178 | 0.39101 | NR | – | Paper | Code | 2018 | linked, not harvested | report |
| 34 | A-DISTS | 0.51717 | 0.53289 | 0.41261 | FR | – | Paper | – | 2021 | no code linked | report |
| 35 | TOPIQ (IAA) | 0.51687 | 0.51061 | 0.40663 | NR | – | Paper | Code | 2023 | 3 of 10 ran · 7 unverified | report |
| 36 | Q-Align (IAA) | 0.51521 | 0.50055 | 0.42211 | NR | – | Paper | Code | 2023 | 2 of 2 ran · 0 unverified | report |
| 37 | ClipIQA+ ViT-L-14 | 0.49881 | 0.50379 | 0.38794 | NR | – | Paper | Code | 2022 | linked, not harvested | report |
| 38 | TReS trained on FLIVE | 0.48882 | 0.50005 | 0.39398 | NR | – | Paper | Code | 2021 | linked, not harvested | report |
| 39 | IL-NIQE | 0.44064 | 0.41892 | 0.34004 | NR | – | – | – | not matched | report | |
| 40 | VMAF Legacy | 0.43296 | 0.39744 | 0.32331 | FR | – | – | – | not matched | report | |
| 41 | VMAF | 0.43219 | 0.40073 | 0.32283 | FR | – | – | – | not matched | report | |
| 42 | TOPIQ + Res50 (IAA) | 0.36204 | 0.34000 | 0.28473 | NR | – | Paper | Code | 2023 | 3 of 10 ran · 7 unverified | report |
| 43 | FSIM | 0.34996 | 0.35083 | 0.26942 | FR | – | Paper | – | 2011 | no code linked | report |
| 44 | VIF | 0.34862 | 0.36944 | 0.26485 | FR | – | – | – | not matched | report | |
| 45 | TOPIQ trained on FLIVE | 0.34092 | 0.33940 | 0.26774 | NR | – | Paper | Code | 2023 | 3 of 10 ran · 7 unverified | report |
| 46 | VILA | 0.33728 | 0.28846 | 0.26180 | NR | – | Paper | Code | 2023 | linked, not harvested | report |
| 47 | NIQE | 0.33167 | 0.33169 | 0.24254 | NR | – | – | – | not matched | report | |
| 48 | BRISQUE | 0.32327 | 0.31143 | 0.24803 | NR | – | Paper | Code | 2012 | linked, not harvested | report |
| 49 | NIMA | 0.25887 | 0.26550 | 0.20377 | NR | – | Paper | Code | 2017 | linked, not harvested | report |
| 50 | MS-SSIM Fast | 0.24422 | 0.21800 | 0.18174 | FR | – | Paper | Code | 2004 | linked, not harvested | report |
| 51 | MS-SSIM Precise | 0.23108 | 0.20935 | 0.17468 | FR | – | Paper | Code | 2004 | linked, not harvested | report |
| 52 | SSIM | 0.22468 | 0.20670 | 0.17175 | FR | – | Paper | – | 2004 | no code linked | report |
| 53 | MS-SSIM Superfast | 0.21604 | 0.30014 | 0.16578 | FR | – | Paper | Code | 2004 | linked, not harvested | report |
| 54 | 3SSIM | 0.21450 | 0.20138 | 0.16365 | FR | – | – | – | not matched | report | |
| 55 | MSAD | 0.17889 | 0.19672 | 0.13551 | FR | – | – | – | not matched | report | |
| 56 | MSE | 0.16441 | 0.09428 | 0.12067 | FR | – | – | – | not matched | report | |
| 57 | PSNR over YUV | 0.14277 | 0.14638 | 0.11040 | FR | – | – | – | not matched | report | |
| 58 | PSNR over Y | 0.12914 | 0.13840 | 0.09998 | FR | – | – | – | not matched | report | |
| 59 | MS-SSIM | 0.11017 | 0.16035 | 0.07821 | FR | – | Paper | Code | 2004 | linked, not harvested | report |
| 60 | BI PSNR | 0.10733 | 0.10931 | 0.08263 | FR | – | – | – | not matched | report |
All 60 rows shown. 48 link to a paper page on this site; 0 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28
Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 24 rows have a graph line, from 10 distinct papers; 23 rows (9 papers) have at least one sample that ran. Counting each paper once: Syntology ran 30 of 68 samples; 38 unverified. Separately, 21 of those 68 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections