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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add scene semantics and multitask scene-specific score adaptation to HyperIQA | HyperIQA · PIQ23, overall image quality | SRCC: 0.611 -> 0.621 | Improved |
| Add scene semantics and multitask scene-specific score adaptation to HyperIQA | HyperIQA · PIQ23, face detail preservation | SRCC: 0.649 -> 0.671 | Improved |
| Add scene semantics and multitask scene-specific score adaptation to HyperIQA | HyperIQA · PIQ23, face target exposure | SRCC: 0.706 -> 0.71 | Improved |
| Use scene-specific rescaling directly instead of predicting a scene category (ablation) | SEM-HyperIQA · PIQ23, face detail preservation | SRCC: 0.671 -> 0.722 | Improved |
| Use scene-specific rescaling directly instead of predicting a scene category (ablation) | SEM-HyperIQA · PIQ23, overall image quality | SRCC: 0.621 -> 0.642 | Improved |
| Use scene-specific rescaling directly instead of predicting a scene category (ablation) | SEM-HyperIQA · PIQ23, face target exposure | SRCC: 0.71 -> 0.721 | Mixed |
| Add scene-specific score rescaling while keeping scene prediction (ablation) | SEM-HyperIQA-CO · PIQ23, face detail preservation | SRCC: 0.664 -> 0.671 | Improved |
| Add scene-specific score rescaling while keeping scene prediction (ablation) | SEM-HyperIQA-CO · PIQ23, face target exposure | SRCC: 0.71 -> 0.71 | No clear effect |
| Add scene-specific score rescaling while keeping scene prediction (ablation) | SEM-HyperIQA-CO · PIQ23, overall image quality | SRCC: 0.621 -> 0.621 | No clear effect |
| Use a deep BIQA model rather than a classical BIQA model | PIQ23 BIQA models · PIQ23, overall image quality | SRCC | Improved |
Closest papers by meaning
- Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption (CVPR 2025 · similarity 0.87)
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · similarity 0.87)
- Image Quality Assessment: From Human to Machine Preference (CVPR 2025 · similarity 0.86)
- Revisiting MLLM Based Image Quality Assessment: Errors and Remedy (AAAI 2026 · similarity 0.86)
- AI-generated Image Quality Assessment in Visual Communication (AAAI 2025 · similarity 0.86)
- Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment (ICLR 2026 · similarity 0.85)
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.
