SOTAVerified

Full reference image quality assessment

The goal is to calculate an objective quality score for a given (potentially) distorted image given its reference (potentially) pristine quality image is available. Training-free metrics are listed.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 50 papers

TitleStatusHype
Digital twins enable full-reference quality assessment of photoacoustic image reconstructions—0
Perceptual Error Logarithm: An Efficient and Effective Analytical Method for Full-Reference Image Quality Assessment—0
Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality AssumptionCode2
BELE: Blur Equivalent Linearized Estimator—0
Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference—0
Image Quality Assessment: Enhancing Perceptual Exploration and Interpretation with Collaborative Feature Refinement and Hausdorff distance—0
Foundation Models Boost Low-Level Perceptual Similarity MetricsCode0
Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment EnhancementCode1
A study of why we need to reassess full reference image quality assessment with medical images—0
Perceptual Quality Assessment for Video Frame Interpolation—0
Show:102550
← PrevPage 1 of 5Next →
All datasetsTID2008ESPLKADID10KDRIQ

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MDSISRCC0.89—Unverified
2HaarPSISRCC0.88—Unverified
3VSISRCC0.88—Unverified
4PELSRCC0.88—Unverified
5FSIMcSRCC0.85—Unverified
6GMSDSRCC0.85—Unverified
7SR-SIMSRCC0.84—Unverified
8FSIMSRCC0.83—Unverified
9MS-SSIMSRCC0.8—Unverified
10VIFSRCC0.65—Unverified