Research map / Image generation / Super-resolution
Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency
Hakan Emre Gedik, Shashank Gupta, Alan Bovik
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 PIE importance weighting instead of mean pooling of patches (ablation) | ReLIQS · KonIQ-10K | SRCC: 0.941 -> 0.949 | Improved |
| add PIE importance weighting instead of mean pooling of patches (ablation) | ReLIQS · UHD | SRCC: 0.861 -> 0.865 | Improved |
| add 512 scale to 224 scale (ablation) | ReLIQS · UHD | SRCC: 0.680 -> 0.750 | Improved |
| add original-resolution scale to 224 and 512 (ablation) | ReLIQS · UHD | SRCC: 0.750 -> 0.865 | Improved |
| add original-resolution scale to 224 and 512 (ablation) | ReLIQS · KonIQ-10K | SRCC: 0.938 -> 0.949 | Improved |
| add multiple scales on lower-resolution datasets (ablation) | ReLIQS · SPAQ, CLIVE, KADID, CSIQ, LIVE | PLCC/SRCC: 0.882 / 0.891 -> 0.891 / 0.894 | No clear effect |
| increase latent quality axes from 1 to 4 (ablation) | ReLIQS · UHD | SRCC: 0.858 -> 0.859 -> 0.865 | Improved |
| increase latent quality axes from 4 to 8 (ablation) | ReLIQS · UHD | SRCC: 0.865 -> 0.863 | No clear effect |
| add margin-ranking loss to PLCC loss (ablation) | ReLIQS · KonIQ-10K | SRCC: 0.941 -> 0.949 | Improved |
| add PLCC loss to margin-ranking loss (ablation) | ReLIQS · KonIQ-10K | PLCC: 0.924 -> 0.958 | Improved |
| use uncertainty-based loss weighting instead of equal weights (ablation) | ReLIQS · KonIQ-10K, SPAQ, KADID multi-dataset | SRCC: 0.944 -> 0.946 | Improved |
| select only top-48 of 748 original-resolution patches by PIE weight | ReLIQS · UHD | SRCC: 748 -> 48 patches | No clear effect |
Closest papers by meaning
- Augmenting Perceptual Super-Resolution via Image Quality Predictors (CVPR 2025 · similarity 0.90)
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · similarity 0.90)
- Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption (CVPR 2025 · similarity 0.89)
- Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing (NeurIPS 2026 · similarity 0.88)
- UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement (CVPR 2026 · similarity 0.87)
- Q-Insight: Understanding Image Quality via Visual Reinforcement Learning (NeurIPS 2025 · 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.
