Research map / Vision-language and multimodal / Cross-modal learning
Unfolding-Associative Encoder-Decoder Network with Progressive Alignment for Pansharpening
Shijie Fang, Hongping Gan
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 sparse multi-scale prior (SE) to SSEM (ablation) | UED-Net · GaoFen-2 simulated | ERGAS: 0.44036 -> 0.42676 | Improved |
| add global degradation awareness (GD) to SSEM (ablation) | UED-Net · GaoFen-2 simulated | ERGAS: 0.44408 -> 0.44036 | Improved |
| use 4 UAAM groups (T=4) instead of 1 (ablation) | UED-Net · GaoFen-2 simulated | ERGAS: 0.43242 -> 0.42676 | Improved |
| add proximal gradient mapping (PG) (ablation) | UED-Net · GaoFen-2 simulated | ERGAS: 0.43683 -> 0.43242 | Improved |
| add ME-Shift (MS) (ablation) | UED-Net · GaoFen-2 simulated | ERGAS: 0.43752 -> 0.43683 | Improved |
| add UAT attention (ablation) | UED-Net · GaoFen-2 simulated | ERGAS: 0.46162 -> 0.43752 | Improved |
| add progressive mechanism (PM) for offsets (ablation) | UED-Net · GaoFen-2 simulated | ERGAS: 0.42885 -> 0.42676 | Improved |
| add deformable convolution (DCN) over standard convolution (ablation) | UED-Net · GaoFen-2 simulated | ERGAS: 0.44419 -> 0.42885 | Improved |
| add progressive mechanism (PM) (ablation) | UED-Net · WorldView-II simulated | ERGAS: 0.83964 -> 0.83493 | Improved |
| add UAT attention (ablation) | UED-Net · WorldView-II simulated | ERGAS: 0.88253 -> 0.83493 | Improved |
| add progressive mechanism (PM) (ablation) | UED-Net · GaoFen-2 real | Ds: 0.07993 -> 0.07011 | Improved |
| add PG and ME-Shift (ablation) | UED-Net · GaoFen-2 real | QNR: 0.8019 -> 0.8667 | Improved |
Closest papers by meaning
- Laboring on less labors: RPCA Paradigm for Pan-sharpening (ICCV 2025 · similarity 0.89)
- SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-Sharpening (AAAI 2025 · similarity 0.88)
- Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks (CVPR 2025 · similarity 0.86)
- Deep Unfolded Network with Intrinsic Supervision for Pan-Sharpening (AAAI 2024 · similarity 0.85)
- HUNet: Homotopy Unfolding Network for Image Compressive Sensing (CVPR 2025 · similarity 0.85)
- UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction (NeurIPS 2026 · similarity 0.84)
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.
