Research map / Image generation / Image restoration
Panchromatic and Multispectral Image Fusion via Alternating Reverse Filtering Network
Keyu Yan, Man Zhou, Jie Huang, Feng Zhao, Chengjun Xie, Chongyi Li, Danfeng Hong
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 supervision L_s with lambda 0.1 (vs lambda 0) (ablation) | ARFNet · WorldView-II | PSNR: 40.1274 -> 41.7587 | Improved |
| Increase lambda from 0.1 to 2 (ablation) | ARFNet · WorldView-II | PSNR: 41.7587 -> 41.0746 | Hurt |
| Increase lambda from 0.1 to 0.5 (ablation) | ARFNet · WorldView-II | SSIM: 0.9691 -> 0.9694 | No clear effect |
| Initialize kernels with Gaussian kernels instead of Kaiming random (ablation) | ARFNet · WorldView-II | PSNR: 40.3297 -> 41.7587 | Improved |
| Initialize kernels with Gaussian kernels instead of Kaiming random (ablation) | ARFNet · WorldView-II | QNR: 0.8097 -> 0.8285 | Improved |
| Increase maximum Gaussian kernel size M from 1 to 17 (ablation) | ARFNet · WorldView-II | PSNR: 39.7820 -> 41.7587 | Improved |
| Increase M from 17 to 21 (ablation) | ARFNet · WorldView-II | PSNR: 41.7587 -> 41.6982 | Hurt |
| Increase iterations K from 1 to 5 (ablation) | ARFNet · WorldView-II | PSNR: 40.7130 -> 41.7587 | Improved |
| Increase iterations K from 5 to 7 (ablation) | ARFNet · WorldView-II | PSNR: 41.7587 -> 41.7603 | No clear effect |
| ARFNet vs SRPPNN on real full-resolution scene | ARFNet · GaoFen2 full-resolution | D_lambda: 0.0767 -> 0.0635 | Improved |
| ARFNet vs SFIM on spatial distortion | ARFNet · GaoFen2 full-resolution | D_s: 0.1087 -> 0.1156 | Hurt |
| ARFNet vs SRPPNN on WV2 | ARFNet · WorldView-II | PSNR: 41.4538 -> 41.7587 | Improved |
Closest papers by meaning
- Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration (AAAI 2024 · similarity 0.92)
- Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion (CVPR 2024 · similarity 0.89)
- Accelerated Diffusion via High-Low Frequency Decomposition for Pan-Sharpening (AAAI 2025 · similarity 0.88)
- SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-Sharpening (AAAI 2025 · similarity 0.88)
- Binarized Neural Network for Multi-spectral Image Fusion (CVPR 2025 · similarity 0.88)
- Frequency-Adaptive Pan-Sharpening with Mixture of Experts (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.
