Research map / Image generation / Autoregressive and latent generation
Fine-grained Image Quality Assessment for Perceptual Image Restoration
Xiangfei Sheng, Xiaofeng Pan, Zhichao Yang, Pengfei Chen, Leida Li
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 |
|---|---|---|---|
| evaluate within narrow MOS ranges instead of the whole dataset | existing IQA metrics (DeQA-Score) · PIPAL | SRCC: 0.747 -> 0.350 | Hurt |
| evaluate within narrow MOS ranges instead of the whole dataset | DB-CNN · PIPAL | SRCC: 0.636 -> -0.016 | Hurt |
| use FGResQ (dual-branch score and ranking) instead of DeQA-Score | FGResQ · FGRestore (average) | pairwise ranking ACC: 0.680 -> 0.752 | Improved |
| use FGResQ instead of DeQA-Score | FGResQ · FGRestore (average) | SRCC: 0.678 -> 0.703 | Improved |
| use FGResQ instead of full-reference A-FINE for ranking | FGResQ · FGRestore (average) | pairwise ranking ACC: 0.736 -> 0.752 | Improved |
| use FGResQ instead of DeQA-Score on deraining | FGResQ · FGRestore Deraining | SRCC: 0.507 -> 0.496 | Hurt |
| use FGResQ instead of DeQA-Score on super-resolution | FGResQ · FGRestore Super-Resolution | SRCC: 0.561 -> 0.521 | Hurt |
| use FGResQ instead of DeQA-Score on dehazing | FGResQ · FGRestore Dehazing | SRCC: 0.762 -> 0.821 | Improved |
| pairwise preference ranking in place of scalar MOS for subtle quality differences | IQA annotation · FGRestore | MOS-preference consistency | Improved |
Closest papers by meaning
- Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption (CVPR 2025 · similarity 0.88)
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · similarity 0.87)
- UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement (CVPR 2026 · similarity 0.87)
- Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference (ICML 2024 · similarity 0.86)
- Augmenting Perceptual Super-Resolution via Image Quality Predictors (CVPR 2025 · similarity 0.86)
- Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment (CVPR 2025 · 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.
