Research map / Image generation / Image restoration
BWAFDA: Block-wise Weighted Attention Fusion with Detail-aware for No-Reference Image Quality Assessment
Shilv Cai, Jian Jin, Tianang Chen, Zhuangzi Li, Weisi Lin
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 detail-aware branch (ablation) | BWAFDA · LIVEFB | SRCC: 0.720 -> 0.723 | Improved |
| add detail-aware branch (ablation) | BWAFDA · LIVEC | PLCC: 0.911 -> 0.928 | Improved |
| add detail-aware branch (ablation) | BWAFDA · LIVEC | SRCC: 0.895 -> 0.917 | Improved |
| add masked prior to attention logits (ablation) | BWAFDA · LIVEFB | PLCC: 0.754 -> 0.777 | Improved |
| add masked prior to attention logits (ablation) | BWAFDA · LIVEFB | SRCC: 0.677 -> 0.723 | Improved |
| add masked prior to attention logits (ablation) | BWAFDA · LIVEC | SRCC: 0.893 -> 0.917 | Improved |
| use three scales instead of one (ablation) | BWAFDA · LIVEFB | SRCC: 0.677 -> 0.723 | Improved |
| use three scales instead of one (ablation) | BWAFDA · LIVEC | PLCC: 0.908 -> 0.928 | Improved |
| use three scales instead of two (ablation) | BWAFDA · LIVEFB | SRCC: 0.678 -> 0.723 | Improved |
| use three scales instead of two (ablation) | BWAFDA · LIVEC | SRCC: 0.895 -> 0.917 | Improved |
| use two scales instead of one (ablation) | BWAFDA · LIVEFB | SRCC: 0.677 -> 0.678 | No clear effect |
| BWAFDA vs SHDIQA in 20% training data | BWAFDA · LIVEC | SRCC: 0.840 -> 0.884 | Improved |
Closest papers by meaning
- Learning Where to Look and How to Judge: Resolution-agnostic Image Quality Assessment with Quality-aware Saliency (CVPR 2026 · similarity 0.88)
- Beyond Cosine Similarity: Magnitude-Aware CLIP for No-Reference Image Quality Assessment (AAAI 2026 · similarity 0.87)
- Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare (NeurIPS 2024 · similarity 0.87)
- Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment (CVPR 2025 · similarity 0.85)
- Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity (ICML 2024 · similarity 0.85)
- Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption (CVPR 2025 · similarity 0.84)
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.
