AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

From Global to Granular: Revealing IQA Model Performance via Correlation Surface

Baoliang Chen, Danni Huang, Hanwei Zhu, Lingyu Zhu, Wei Zhou, Shiqi Wang, Yuming Fang, Weisi Lin

TPAMI 2026 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add kernel-smoothed density estimation to the Distribution Regulator (ablation)GMC · PIPAL (50 extreme sampling trials)average std of GMC_g: 0.1664 -> 0.1651Improved
add kernel-smoothed density estimation to the Distribution Regulator (ablation)GMC · SPAQ (50 extreme sampling trials)average std of GMC_g: 0.1778 -> 0.1737Improved
add kernel-smoothed density estimation to the Distribution Regulator (ablation)GMC · AIGCIQA2023 (50 extreme sampling trials)average std of GMC_g: 0.1783 -> 0.1626Improved
use Latin Hypercube Sampling instead of random sampling for surface points (ablation)GMC_g · PIPAL/SPAQ sampling size studystability of GMC_gImproved
select the best model with GMC_s instead of SRCC for high-quality retrievalIQA model selection · SPAQ high-quality setmean MOS of top-3: 76.37 -> 86.17Improved
select the best model with GMC_s instead of SRCC for high-quality retrievalIQA model selection · KADID-10k high-quality setmean MOS of top-3: 4.68 -> 4.75Improved
select the best model with GMC_s instead of SRCC for AIGC quality retrievalIQA model selection · AGIQA-3K quality setmean MOS of top-3: 3.48 -> 4.14Improved
integrate LPIPS with MS-SSIM (GMC-suggested) rather than DISTSIQA model integration · PIPALSRCC: 0.6019 -> 0.6202Improved
use GMC_g instead of SRCC under shifted MOS distributionsevaluation metric · PIPAL and SPAQ nine sampled subsetsvariability across subsetsImproved
optimize MS-SSIM instead of LPIPS or DISTS under adversarial constraintfine-grained image optimization · PIPALvisual quality of optimized imagesImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy