Research map / Image generation / Autoregressive and latent generation
Group MAD Competition - A New Methodology to Compare Objective Image Quality Models
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use multi-scale SSIM instead of SSIM | SSIM · gMAD competition on the new IQA database | global ranking | Helped |
| Use FR-IQA models rather than NR-IQA models | IQA models · gMAD competition on the new IQA database | global ranking | Helped |
| Use perception- and distortion-relevant natural scene statistics features | NR-IQA models · gMAD competition on the new IQA database | global ranking | Helped |
| Use LPSI's one-dimensional feature space without MOS training instead of sophisticated machine-learning approaches | NR-IQA models · gMAD competition on the new IQA database | global ranking | Helped |
| Train IQA models on existing publicly available databases | Machine-learning-based IQA models · gMAD competition on the new IQA database | global ranking | Hurt |
| Use training-based IQA models rather than non-training-based models | IQA models · Rational consistency test on the new IQA database | KRCC consistency | Hurt |
| Use FR-IQA models rather than NR-IQA models | IQA models · Rational consistency test on the new IQA database | KRCC consistency | Helped |
| Evaluate models with gMAD-selected image pairs instead of relying only on pre-defined subject-rated samples | IQA model comparison · New IQA database | subjective discrimination | Helped |
Closest papers by meaning
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · similarity 0.91)
- Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption (CVPR 2025 · similarity 0.91)
- Image Quality Assessment: From Human to Machine Preference (CVPR 2025 · similarity 0.90)
- IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring (ICML 2026 · similarity 0.88)
- Augmenting Perceptual Super-Resolution via Image Quality Predictors (CVPR 2025 · similarity 0.87)
- Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference (ICML 2024 · similarity 0.87)
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.