Research map / Vision-language and multimodal / Cross-modal learning
Probability-Based Global Cross-Modal Upsampling for Pansharpening
Zeyu Zhu, Xiangyong Cao, Man Zhou, Junhao Huang, Deyu Meng
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 |
|---|---|---|---|
| Replace PanNet upsampling with PGCU | PanNet · WorldView2 | PSNR: 37.459 -> 41.659 | Improved |
| Replace PanNet upsampling with PGCU | PanNet · GaoFen2 | PSNR: 42.619 -> 46.715 | Improved |
| Replace GPPNN upsampling with PGCU | GPPNN · WorldView2 | PSNR: 41.190 -> 41.659 | Improved |
| Replace GPPNN upsampling with PGCU | GPPNN · GaoFen2 | PSNR: 46.566 -> 47.815 | Improved |
| Increase PanNet ResNet blocks to match PGCU parameter count | PanNet · GaoFen2 | PSNR: 42.619 -> 42.630 | Improved |
| Replace local upsampling with PGCU rather than only increasing model parameters | PanNet · GaoFen2 | PSNR: 42.630 -> 46.715 | Improved |
| Set feature vector length to 32 rather than 128 (ablation) | PGCU · GaoFen2 | PSNR: 46.715 -> 43.722 | Hurt |
| Set feature vector length to 64 rather than 128 (ablation) | PGCU · GaoFen2 | PSNR: 46.715 -> 45.334 | Hurt |
| Set feature vector length to 96 rather than 128 (ablation) | PGCU · GaoFen2 | PSNR: 46.715 -> 46.166 | Hurt |
| Increase feature vector length from 128 to 160 (ablation) | PGCU · GaoFen2 | PSNR: 46.715 -> 46.436 | Hurt |
| Increase feature vector length from 128 to 192 (ablation) | PGCU · GaoFen2 | PSNR: 46.715 -> 46.003 | Hurt |
| Add PAN information (ablation) | PGCU · GaoFen2 | PSNR: 46.181 -> 46.715 | Improved |
Closest papers by meaning
- Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables (NeurIPS 2025 · similarity 0.87)
- SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening (NeurIPS 2024 · similarity 0.87)
- PanAdapter: Two-Stage Fine-Tuning with Spatial-Spectral Priors Injecting for Pansharpening (AAAI 2025 · similarity 0.87)
- Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening (CVPR 2024 · similarity 0.86)
- A General Adaptive Dual-level Weighting Mechanism for Remote Sensing Pansharpening (CVPR 2025 · similarity 0.85)
- Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration (AAAI 2024 · 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.
