Research map / Image generation / Image restoration
Learned Image Reasoning Prior Penetrates Deep Unfolding Network for Panchromatic and Multi-spectral Image Fusion
Man Zhou, Jie Huang, Naishan Zheng, Chongyi Li
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 pre-trained MAE reasoning prior inside the unfolding network (U_MAE) (ablation) | MAE-prior unfolding network · WorldView-II | PSNR: 41.4655 -> 41.6576 | Improved |
| add MAE spatial-spectral regularization in the loss (L_MAE) (ablation) | MAE-prior unfolding network · WorldView-II | PSNR: 41.4655 -> 41.8382 | Improved |
| use both MAE prior and MAE loss together versus either alone (ablation) | MAE-prior unfolding network · WorldView-II | PSNR: 41.8382 -> 41.8735 | Improved |
| increase number of unfolding stages from 1 to 4 (ablation) | MAE-prior unfolding network · WorldView-II | PSNR: 41.2459 -> 41.8735 | Improved |
| increase number of unfolding stages beyond 4 (to 5 and 6) (ablation) | MAE-prior unfolding network · WorldView-II | PSNR: 41.8735 -> 41.8461 (K=5), 41.7429 (K=6) | Hurt |
| replace prior pan-sharpening SOTA (MANet) with the MAE-prior unfolding method | Pan-sharpening · GaoFen2 | PSNR: 47.2668 -> 47.3931 | Improved |
| MAE-prior unfolding on full-resolution scenes versus baselines | Pan-sharpening · GaoFen2 (full resolution) | D_s: SFIM 0.1087 vs Ours 0.1112 | No clear effect |
Closest papers by meaning
- SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-Sharpening (AAAI 2025 · similarity 0.92)
- Memory-Augmented Model-Driven Network for Pansharpening (ECCV 2022 · similarity 0.91)
- Deep Unfolded Network with Intrinsic Supervision for Pan-Sharpening (AAAI 2024 · similarity 0.90)
- Unsupervised Pan-Sharpening via Mutually Guided Detail Restoration (AAAI 2024 · similarity 0.87)
- U-Know-DiffPAN: An Uncertainty-aware Knowledge Distillation Diffusion Framework with Details Enhancement for PAN-Sharpening (CVPR 2025 · similarity 0.86)
- PanAdapter: Two-Stage Fine-Tuning with Spatial-Spectral Priors Injecting for Pansharpening (AAAI 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.
