AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

An Image Quality Assessment Dataset for Portraits

Nicolas Chahine, Stefania Calarasanu, Davide Garcia-Civiero, Théo Cayla, Sira Ferradans, Jean Ponce

CVPR 2023 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 22 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 scene semantics and multitask scene-specific score adaptation to HyperIQAHyperIQA · PIQ23, overall image qualitySRCC: 0.611 -> 0.621Improved
Add scene semantics and multitask scene-specific score adaptation to HyperIQAHyperIQA · PIQ23, face detail preservationSRCC: 0.649 -> 0.671Improved
Add scene semantics and multitask scene-specific score adaptation to HyperIQAHyperIQA · PIQ23, face target exposureSRCC: 0.706 -> 0.71Improved
Use scene-specific rescaling directly instead of predicting a scene category (ablation)SEM-HyperIQA · PIQ23, face detail preservationSRCC: 0.671 -> 0.722Improved
Use scene-specific rescaling directly instead of predicting a scene category (ablation)SEM-HyperIQA · PIQ23, overall image qualitySRCC: 0.621 -> 0.642Improved
Use scene-specific rescaling directly instead of predicting a scene category (ablation)SEM-HyperIQA · PIQ23, face target exposureSRCC: 0.71 -> 0.721Mixed
Add scene-specific score rescaling while keeping scene prediction (ablation)SEM-HyperIQA-CO · PIQ23, face detail preservationSRCC: 0.664 -> 0.671Improved
Add scene-specific score rescaling while keeping scene prediction (ablation)SEM-HyperIQA-CO · PIQ23, face target exposureSRCC: 0.71 -> 0.71No clear effect
Add scene-specific score rescaling while keeping scene prediction (ablation)SEM-HyperIQA-CO · PIQ23, overall image qualitySRCC: 0.621 -> 0.621No clear effect
Use a deep BIQA model rather than a classical BIQA modelPIQ23 BIQA models · PIQ23, overall image qualitySRCCImproved

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