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

Showing 125 of 155 papers

TitleStatusHype
TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality AssessmentCode4
Pairwise Comparisons Are All You NeedCode2
Exploring CLIP for Assessing the Look and Feel of ImagesCode2
LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment ModelCode2
Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning PerspectiveCode2
SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction TuningCode2
MANIQA: Multi-dimension Attention Network for No-Reference Image Quality AssessmentCode2
Generalizable No-Reference Image Quality Assessment via Deep Meta-learningCode1
Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality AssessmentCode1
High Resolution Image Quality DatabaseCode1
Blind Image Quality Assessment Based on Geometric Order LearningCode1
DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the WildCode1
Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality AssessmentCode1
ARNIQA: Learning Distortion Manifold for Image Quality AssessmentCode1
Data-Efficient Image Quality Assessment with Attention-Panel DecoderCode1
Continual Learning for Blind Image Quality AssessmentCode1
Deep Feature Statistics Mapping for Generalized Screen Content Image Quality AssessmentCode1
Blind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality TokenCode1
Analysis of Video Quality Datasets via Design of Minimalistic Video Quality ModelsCode1
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper NetworkCode1
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to CompareCode1
Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable BankCode1
A CNN-Based Blind Denoising Method for Endoscopic ImagesCode1
Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm RegularizationCode1
Conformer and Blind Noisy Students for Improved Image Quality AssessmentCode1
Show:102550
← PrevPage 1 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RvTC (image-only)SRCC0.98Unverified
2UNIQASRCC0.94Unverified
3CONTRIQUESRCC0.93Unverified
4ARNIQASRCC0.91Unverified
5Re-IQASRCC0.87Unverified
6TReSSRCC0.86Unverified
7HyperIQASRCC0.85Unverified
8DB-CNNSRCC0.85Unverified
9BRISQUESRCC0.53Unverified
#ModelMetricClaimedVerifiedStatus
1UNIQASRCC0.96Unverified
2ARNIQASRCC0.96Unverified
3Re-IQASRCC0.95Unverified
4DB-CNNSRCC0.95Unverified
5CONTRIQUESRCC0.94Unverified
6HyperIQASRCC0.92Unverified
7TReSSRCC0.92Unverified
8BRISQUESRCC0.75Unverified
#ModelMetricClaimedVerifiedStatus
1UNIQASRCC0.95Unverified
2ARNIQASRCC0.88Unverified
3TReSSRCC0.86Unverified
4CONTRIQUESRCC0.84Unverified
5HyperIQASRCC0.84Unverified
6DB-CNNSRCC0.82Unverified
7Re-IQASRCC0.8Unverified
8BRISQUESRCC0.6Unverified
#ModelMetricClaimedVerifiedStatus
1LAR-IQA (KAN head)SRCC0.84Unverified
2QualiCLIPSRCC0.77Unverified
3CLIP-IQA+SRCC0.75Unverified
4ARNIQASRCC0.74Unverified
5CONTRIQUESRCC0.73Unverified
6Effnet-2C-MLSPSRCC0.68Unverified
7HyperIQASRCC0.55Unverified
#ModelMetricClaimedVerifiedStatus
1RvTC (image-only)PLCC0.95Unverified
#ModelMetricClaimedVerifiedStatus
1UNIQASRCC0.99Unverified
#ModelMetricClaimedVerifiedStatus
1RvTC (image-only)PLCC0.93Unverified