List your company
ResearchFormerly WizWand

No-Reference Image Quality Assessment on KADID (test)

0.934SROCCCONTRIQUE
0.332880.488940.6450.80106Oct 25, 2021Jul 7, 2022Mar 20, 2023Nov 30, 2023Aug 12, 2024Apr 24, 2025Jan 5, 2026
Updated 8mo ago

Evaluation results

MethodLinks
CONTRIQUEModel Type=Unsupervised pretraining and Linear Regression2021.100.9340.937
HyperIQAModel Type=Supervised pretraining and supervised fine-tuning2021.100.8520.845
DB-CNNModel Type=Supervised pretraining and supervised fine-tuning2021.100.8510.856
OursCategory=SFT-based and RL-based MLLMs, Condition=Image-conditioned2025.120.7340.672
Q-Insight-ScoreModel category=SFT-based and RL-based MLLMs, Input Condition=Image-conditioned2026.010.7020.702
Q-Insight-ScoreCategory=SFT-based and RL-based MLLMs, Condition=Image-conditioned2025.120.7020.702
Resnet-50Model Type=Supervised pretraining and Linear Regression2021.100.7010.677
Autoencoder-likeModel category=SFT-based and RL-based MLLMs, Input Condition=Image-conditioned2026.010.70.649
Chain-of-ThoughtModel category=SFT-based and RL-based MLLMs, Input Condition=Image-conditioned2026.010.6990.629
Self-ConsistencyModel category=SFT-based and RL-based MLLMs, Input Condition=Image-conditioned2026.010.6920.632
DeQAModel category=SFT-based and RL-based MLLMs, Input Condition=Image-conditioned2026.010.6870.694
DeQACategory=SFT-based and RL-based MLLMs, Condition=Image-conditioned2025.120.6870.694
Q-AlignModel category=SFT-based and RL-based MLLMs, Input Condition=Image-conditioned2026.010.6840.674
Q-AlignCategory=SFT-based and RL-based MLLMs, Condition=Image-conditioned2025.120.6840.674
OursCategory=Caption-Only Conditions, Condition=Caption-Only2025.120.6760.662
Self-ConsistencyInput Condition=Text-Only2026.010.6610.627
Self-ConsistencyInput Condition=Text-Only, Text Filtering=Score-related words removed2026.010.660.632
CLIP-IQA+Model category=Deep-Learning Models, Input Condition=Image-conditioned2026.010.6540.653
CLIP-IQA+Category=Deep-Learning Models, Condition=Image-conditioned2025.120.6540.653
Q-Insight-ScoreCategory=Caption-Only Conditions, Condition=Caption-Only2025.120.650.645
Autoencoder-likeInput Condition=Text-Only2026.010.6450.632
Autoencoder-likeInput Condition=Text-Only, Text Filtering=Score-related words removed2026.010.6440.638
Q-Insight-ScoreInput Condition=Text-Only, Text Filtering=Score-related words removed2026.010.6210.611
Chain-of-ThoughtInput Condition=Text-Only, Text Filtering=Score-related words removed2026.010.6210.609
Q-Insight-ScoreInput Condition=Text-Only2026.010.620.604
Chain-of-ThoughtInput Condition=Text-Only2026.010.620.604
HOSAModel Type=Codebook-based Features2021.100.6180.653
MUSIQModel category=Deep-Learning Models, Input Condition=Image-conditioned2026.010.5560.575
MUSIQCategory=Deep-Learning Models, Condition=Image-conditioned2025.120.5560.575
NIMAModel category=Deep-Learning Models, Input Condition=Image-conditioned2026.010.5350.532
NIMACategory=Deep-Learning Models, Condition=Image-conditioned2025.120.5350.532
BRISQUEModel Type=Traditional/Handcrafted Features2021.100.5280.567
CORNIAModel Type=Codebook-based Features2021.100.5160.558
DBCNNModel category=Deep-Learning Models, Input Condition=Image-conditioned2026.010.4840.497
DBCNNCategory=Deep-Learning Models, Condition=Image-conditioned2025.120.4840.497
MANIQAModel category=Deep-Learning Models, Input Condition=Image-conditioned2026.010.4650.499
MANIQACategory=Deep-Learning Models, Condition=Image-conditioned2025.120.4650.499
C2ScoreModel category=SFT-based and RL-based MLLMs, Input Condition=Image-conditioned2026.010.4530.5
C2ScoreCategory=SFT-based and RL-based MLLMs, Condition=Image-conditioned2025.120.4530.5
NIQECategory=Hand-Crafted Models, Condition=Image-conditioned2025.120.4050.468
NIQEModel Type=Traditional/Handcrafted Features2021.100.3740.428
BRISQUECategory=Hand-Crafted Models, Condition=Image-conditioned2025.120.3560.429