List your company
ResearchFormerly WizWand

No-reference Image Quality Assessment on PIPAL

0.649PLCCEvoQuality
0.098840.241670.38450.52733Sep 30, 2025Oct 28, 2025Nov 26, 2025Dec 25, 2025Jan 22, 2026Feb 20, 2026Mar 21, 2026
Updated 4mo ago

Evaluation results

MethodLinks
EvoQualityModel Category=VLM-based, Zero-shot evaluation=true, Evolution Round=Round 22025.090.6490.583
ME-IQABase VLM=EvoQuality2026.030.6420.588
ME-IQABase VLM=Q-Insight2026.030.6350.566
EvoQualityModel Category=VLM-based, Zero-shot evaluation=true, Evolution Round=Round 12025.090.6130.545
DeQA-ScoreModel Type=Non-reasoning2026.030.6080.565
DeQA-ScoreModel Category=VLM-based, Zero-shot evaluation=true2025.090.6080.565
Q-InsightModel Category=VLM-based, Zero-shot evaluation=true2025.090.6080.534
BaselineBase VLM=Q-Insight2026.030.6040.528
MANIQAModel Type=Non-reasoning2026.030.6030.551
MANIQAModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.090.6030.551
BaselineBase VLM=EvoQuality2026.030.6020.543
Q-AlignModel Type=Non-reasoning2026.030.60.518
Q-AlignModel Category=VLM-based, Zero-shot evaluation=true2025.090.60.518
ME-IQABase VLM=VisualQuality-R12026.030.5990.551
Compare2ScoreModel Type=Non-reasoning2026.030.5960.588
MUSIQModel Type=Non-reasoning2026.030.5670.535
BaselineBase VLM=VisualQuality-R12026.030.5670.509
MUSIQModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.090.5670.535
ME-IQABase VLM=GPT-52026.030.5660.56
ME-IQABase VLM=Doubao-Seed-1.6-vision2026.030.5610.533
CLIP-IQA+Model Type=Non-reasoning2026.030.550.499
CLIP-IQA+Model Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.090.550.499
BaselineBase VLM=GPT-52026.030.5390.496
NIMAModel Type=Non-reasoning2026.030.5360.486
NIMAModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.090.5360.486
VisualQuality-R1Model Category=VLM-based, Zero-shot evaluation=true2025.090.5310.486
BaselineBase VLM=Doubao-Seed-1.6-vision2026.030.5170.483
HyperIQAModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.090.5110.461
DBCNNModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.090.4690.408
Qwen2.5-VL-7BModel Category=VLM-based, Zero-shot evaluation=true2025.090.4440.388
CONTRIQUEModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.090.4160.341
BRISQUEModel Category=Handcrafted, Zero-shot evaluation=true2025.090.4120.279
NIQEModel Category=Handcrafted, Zero-shot evaluation=true2025.090.3720.12
Re-IQAModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.090.3540.281
NIQEModel Type=Non-reasoning2026.030.120.12