SOTAVerified

No-Reference Image Quality Assessment

An Image Quality Assessment approach where no reference image information is available to the model. Sometimes referred to as Blind Image Quality Assessment (BIQA).

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 155 papers

TitleStatusHype
Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression—0
DGIQA: Depth-guided Feature Attention and Refinement for Generalizable Image Quality AssessmentCode0
Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality AssessmentCode1
Cross-Domain Underwater Image Enhancement Guided by No-Reference Image Quality Assessment: A Transfer Learning Approach—0
IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond—0
Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable TriggerCode0
Light Field Image Quality Assessment With Auxiliary Learning Based on Depthwise and Anglewise Separable Convolutions—0
A No-Reference Medical Image Quality Assessment Method Based on Automated Distortion Recognition Technology: Application to Preprocessing in MRI-guided Radiotherapy—0
Dual-Representation Interaction Driven Image Quality Assessment with Restoration AssistanceCode0
Stochastic BIQA: Median Randomized Smoothing for Certified Blind Image Quality Assessment—0
Show:102550
← PrevPage 1 of 16Next →
All datasetsKADID-10kCSIQTID2013UHD-IQAKonIQ-10kLIVESPAQ

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1LAR-IQA (KAN head)SRCC0.84—Unverified
2QualiCLIPSRCC0.77—Unverified
3CLIP-IQA+SRCC0.75—Unverified
4ARNIQASRCC0.74—Unverified
5CONTRIQUESRCC0.73—Unverified
6Effnet-2C-MLSPSRCC0.68—Unverified
7HyperIQASRCC0.55—Unverified