Research map / Video / Video segmentation and tracking
Video Can Teach PAN-Sharpening: PSF-Aware Cross-Domain Supervision
Hyun-Ho Kim, Munchurl Kim, Jaehyup Lee
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 video-derived spatial supervision (L_spa) (ablation) | ViPS · WV3 full-resolution | HQNR: 0.949 -> 0.959 | Improved |
| add video-derived spatial supervision (L_spa) (ablation) | ViPS · WV3 full-resolution | Ds: 0.036 -> 0.026 | Improved |
| add video-derived spatial supervision (L_spa) (ablation) | ViPS · WV3 reduced-resolution | PSNR: 37.118 -> 38.021 | Improved |
| add shared PSF-bank degradation across branches (ablation) | ViPS · WV3 reduced-resolution | PSNR: 37.277 -> 38.021 | Improved |
| add shared PSF-bank degradation across branches (ablation) | ViPS · WV3 full-resolution | HQNR: 0.956 -> 0.959 | Improved |
| add random PSF kernel sampling (ablation) | ViPS · WV3 full-resolution | Dlambda: 0.023 -> 0.016 | Improved |
| add random PSF kernel sampling (ablation) | ViPS · WV3 reduced-resolution | SAM: 3.190 -> 2.770 | Improved |
| add random PSF kernel sampling (ablation) | ViPS · WV3 full-resolution | HQNR: 0.948 -> 0.959 | Improved |
| train PanNet with ViPS supervision (ablation) | PanNet · WV3 full-resolution | HQNR: 0.918 -> 0.954 | Improved |
| train PanNet with ViPS supervision (ablation) | PanNet · WV3 reduced-resolution | PSNR: 36.148 -> 37.229 | Improved |
| increase temporal offset a from 1 to 10 (ablation) | ViPS · WV3 reduced-resolution | PSNR: 37.359 -> 38.021 | Improved |
| increase temporal offset a from 10 to 20 (ablation) | ViPS · WV3 reduced-resolution | PSNR: 38.021 -> 37.013 | Hurt |
Closest papers by meaning
- PAN-Crafter: Learning Modality-Consistent Alignment for PAN-Sharpening (ICCV 2025 · similarity 0.89)
- Deep Unfolded Network with Intrinsic Supervision for Pan-Sharpening (AAAI 2024 · similarity 0.87)
- Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration (AAAI 2024 · similarity 0.87)
- 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 0.86)
- U-Know-DiffPAN: An Uncertainty-aware Knowledge Distillation Diffusion Framework with Details Enhancement for PAN-Sharpening (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.
