Research map / Image generation / Image restoration
Memory-Augmented Model-Driven Network for Pansharpening
Keyu Yan, Man Zhou, Li Zhang, Chengjun Xie
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 CNL and multi-location memory (MM) to the K=4 baseline (ablation) | MMNet · WorldView-II | PSNR: 41.4325 -> 41.8577 | Improved |
| increase unfolded stages from 1 to 4 (ablation) | MMNet · WorldView-II | PSNR: 41.2772 -> 41.8577 | Improved |
| increase unfolded stages from 4 to 5 (ablation) | MMNet · WorldView-II | PSNR: 41.8577 -> 41.7545 | Hurt |
| use stage number 3 instead of 4 (ablation) | MMNet · WorldView-II | PSNR: 41.8058 -> 41.8577 | No clear effect |
| use MMNet instead of SRPPNN | pan-sharpening network · WorldView-II | PSNR: 41.4538 -> 41.8577 | Improved |
| use MMNet instead of GPPNN | pan-sharpening network · WorldView-II | PSNR: 41.1622 -> 41.8577 | Improved |
| use MMNet instead of SRPPNN | pan-sharpening network · GaoFen2 | PSNR: 47.1998 -> 47.2668 | Improved |
| use MMNet instead of SRPPNN | pan-sharpening network · WorldView-III | PSNR: 30.4346 -> 30.5451 | Improved |
| use MMNet instead of MSDCNN | pan-sharpening network · GaoFen2 full-resolution | QNR: 0.8251 -> 0.8235 | No clear effect |
| use MMNet instead of GPPNN | pan-sharpening network · GaoFen2 full-resolution | QNR: 0.8073 -> 0.8235 | Improved |
Closest papers by meaning
- Deep Unfolded Network with Intrinsic Supervision for Pan-Sharpening (AAAI 2024 · similarity 0.91)
- SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-Sharpening (AAAI 2025 · similarity 0.91)
- Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration (AAAI 2024 · similarity 0.86)
- Progressive High-Frequency Reconstruction for Pan-Sharpening with Implicit Neural Representation (AAAI 2024 · similarity 0.86)
- PanAdapter: Two-Stage Fine-Tuning with Spatial-Spectral Priors Injecting for Pansharpening (AAAI 2025 · similarity 0.85)
- U-Know-DiffPAN: An Uncertainty-aware Knowledge Distillation Diffusion Framework with Details Enhancement for PAN-Sharpening (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.
