Research map / Architectures and efficiency / Attention and transformers
Multi-Head Attention Residual Unfolded Network for Model-Based Pansharpening
Ivan Pereira-Sánchez, Eloi Sans, Julia Navarro, Joan Duran
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 MARNet post-processing (ablation) | MARNet unfolded network · PRISMA | PSNR: 41,53 -> 41,72 | Improved |
| add MARNet post-processing (ablation) | MARNet unfolded network · PRISMA | ERGAS: 26,23 -> 25,77 | Improved |
| use MARNet instead of ResNet for post-processing (ablation) | MARNet unfolded network · PRISMA | PSNR: 37,92 -> 41,72 | Improved |
| use MARNet instead of CNN for post-processing (ablation) | MARNet unfolded network · PRISMA | PSNR: 41,29 -> 41,72 | Improved |
| add a CNN post-processing module (ablation) | MARNet unfolded network · PRISMA | PSNR: 41,53 -> 41,29 | Hurt |
| add a ResNet post-processing module (ablation) | MARNet unfolded network · PRISMA | SAM: 2,74 -> 5,42 | Hurt |
| increase sampling factor from 4 to 36 | MARNet unfolded network · Pelican | PSNR: 47,70 -> 33,91 | Hurt |
| increase sampling factor from 4 to 12 | MARNet unfolded network · Pelican | PSNR: 47,70 -> 39,63 | Hurt |
| increase noise sigma from 0 to 50 | MARNet unfolded network · Pelican (s=4) | PSNR: 47,70 -> 33,92 | Hurt |
| increase noise sigma from 0 to 5 | MARNet unfolded network · Pelican (s=4) | PSNR: 47,70 -> 40,95 | Hurt |
| use the unfolded MARNet instead of SRPPNN on PRISMA | MARNet unfolded network · PRISMA | SSIM: 0,9676 -> 0,9673 | No clear effect |
| use the unfolded MARNet instead of MMNet on QuickBird | MARNet unfolded network · QuickBird | PSNR: 40,74 -> 40,68 | No clear effect |
Closest papers by meaning
- Memory-Augmented Deep Conditional Unfolding Network for Pan-Sharpening (CVPR 2022 · similarity 0.90)
- Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening (AAAI 2025 · similarity 0.88)
- PanAdapter: Two-Stage Fine-Tuning with Spatial-Spectral Priors Injecting for Pansharpening (AAAI 2025 · similarity 0.88)
- Deep Unfolded Network with Intrinsic Supervision for Pan-Sharpening (AAAI 2024 · similarity 0.87)
- SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-Sharpening (AAAI 2025 · similarity 0.87)
- Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration (AAAI 2024 · 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.
