Research map / Image generation / Super-resolution
From Coarse to Fine: Hierarchical Pixel Integration for Lightweight Image Super-resolution
Read the paperCheck 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 |
|---|---|---|---|
| Add Cascaded Patch Division (CPD) (ablation) | HPINet without CPD or GPA · Set5 ×4 | PSNR: 32.46 -> 32.50 | Helped |
| Add CPD (ablation) | HPINet without CPD or GPA · Set14 ×4 | LPIPS: 0.2844 -> 0.2817 | Helped |
| Add Global Pixel Access (GPA) (ablation) | HPINet without CPD or GPA · Set5 ×4 | PSNR: 32.46 -> 32.50 | Helped |
| Add GPA (ablation) | HPINet with CPD · All five benchmarks ×4 | PSNR: 32.50 -> 32.60; 28.83 -> 28.87; 27.71 -> 27.73; 26.63 -> 26.71; 31.04 -> 31.19 | Helped |
| Add GPA to the baseline without CPD (ablation) | HPINet without CPD · Set14 ×4 | LPIPS: 0.2844 -> 0.2868 | Hurt |
| Add CPD alongside GPA (ablation) | HPINet with GPA · Set14 ×4 | LPIPS: 0.2868 -> 0.2826 | Helped |
| Add Intra-Patch Self-Attention (IPSA) instead of depth-wise convolutions (ablation) | HPINet · All five benchmarks ×4 | PSNR: 32.26 -> 32.60; 28.66 -> 28.87; 27.60 -> 27.73; 26.30 -> 26.71; 30.66 -> 31.19 | Helped |
| Add the 3×3 convolution for local detail processing (ablation) | HPINet · All five benchmarks ×4 | PSNR: 32.09 -> 32.60; 28.63 -> 28.87; 27.57 -> 27.73; 26.17 -> 26.71; 30.55 -> 31.19 | Helped |
Closest papers by meaning
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.88)
- CFAT: Unleashing Triangular Windows for Image Super-resolution (CVPR 2024 · similarity 0.87)
- Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution (AAAI 2025 · similarity 0.87)
- CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution (CVPR 2025 · similarity 0.86)
- HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution (CVPR 2025 · similarity 0.86)
- Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach (CVPR 2025 · similarity 0.86)
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.