Research map / Image generation / Image restoration
Mutual Information-Driven Pan-Sharpening
Check 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 |
|---|---|---|---|
| Use mutual information minimization between PAN and MS feature embeddings (ablation) | Ours · WorldView II | PSNR: 41.4940 -> 41.6773 | Helped |
| Use mutual information minimization between PAN and MS feature embeddings (ablation) | Ours · GaoFen2 | PSNR: 47.2316 -> 47.3042 | Helped |
| Use mutual information minimization between PAN and MS feature embeddings (ablation) | Ours · WorldView III | PSNR: 30.2893 -> 30.4907 | Helped |
| Use INN instead of a parameter-matched ResNet fusion block (ablation) | Ours · WorldView II | PSNR: 41.5863 -> 41.6773 | Helped |
| Use INN instead of a parameter-matched ResNet fusion block (ablation) | Ours · GaoFen2 | PSNR: 47.2775 -> 47.3042 | Helped |
| Use INN instead of a parameter-matched ResNet fusion block (ablation) | Ours · WorldView III | PSNR: 30.3511 -> 30.4907 | Helped |
| Set mutual-information loss weight λ to 0.1 rather than 0.01, 0.05, 0.5, or 1 (ablation) | Ours · WorldView II | PSNR: 41.5859; 41.6079; 41.6773; 41.5581; 41.4867 | Mixed |
| Use the proposed method instead of SRPPNN | Pan-sharpening models · WorldView II | PSNR: 41.4538 -> 41.6773 | Helped |
| Use the proposed method instead of SRPPNN | Pan-sharpening models · GaoFen2 | PSNR: 47.1998 -> 47.3042 | Helped |
| Use the proposed method instead of SRPPNN | Pan-sharpening models · WorldView III | PSNR: 30.4346 -> 30.4907 | Helped |
| Use the proposed method instead of MSDCNN | Pan-sharpening models · Full-resolution dataset | QNR: 0.8215 -> 0.8259 | Helped |
Closest papers by meaning
- Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration (AAAI 2024 · similarity 0.89)
- Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion (CVPR 2024 · similarity 0.88)
- Frequency-Adaptive Pan-Sharpening with Mixture of Experts (AAAI 2024 · similarity 0.88)
- SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-Sharpening (AAAI 2025 · similarity 0.87)
- Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables (NeurIPS 2025 · similarity 0.87)
- U-Know-DiffPAN: An Uncertainty-aware Knowledge Distillation Diffusion Framework with Details Enhancement for PAN-Sharpening (CVPR 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.