Research map / Image generation / Super-resolution
Deep Blind Hyperspectral Image Fusion
Wu Wang, Weihong Zeng, Yue Huang, Xinghao Ding, John Paisley
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 |
|---|---|---|---|
| increase iterations from 1 to 5 with shared parameters (ablation) | DBIN · CAVE | PSNR: 45.58 -> 46.32 | Improved |
| increase iterations from 1 to 3 (ablation) | DBIN · CAVE | PSNR: 45.58 -> 45.69 | Improved |
| increase iterations from 3 to 5 (ablation) | DBIN · CAVE | ERGAS: 0.69 -> 0.66 | Improved |
| add dense fusion of all iteration outputs (ablation) | DBIN (n=5) · CAVE | PSNR: 46.32 -> 47.51 | Improved |
| add dense fusion of all iteration outputs (ablation) | DBIN (n=5) · CAVE | SAM: 3.41 -> 3.18 | Improved |
| use multiple convolution kernels of different sizes for observation model (ablation) | DBIN+ · CAVE | performance | No clear effect |
| blind DBIN+ instead of non-blind DHSIS | DBIN+ · CAVE (non-blind) | PSNR: 45.59 -> 47.51 | Improved |
| blind DBIN+ instead of non-blind NSSR | DBIN+ · Harvard (non-blind) | PSNR: 46.31 -> 46.67 | Improved |
| blind DBIN+ instead of blind HySure | DBIN+ · NTIRE2018 (semi-blind) | PSNR: 37.3 -> 46.4 | Improved |
| preset R matrix used by non-blind DHSIS when R is unknown | DHSIS · NTIRE2018 (semi-blind) | PSNR: 45.59 -> 1.13 | Hurt |
Closest papers by meaning
- Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net (CVPR 2019 · similarity 0.88)
- MHF-Net: An Interpretable Deep Network for Multispectral and Hyperspectral Image Fusion (TPAMI 2020 · similarity 0.88)
- Hyperspectral Image Fusion with Spectral-Band and Fusion-Scale Agnosticism (ICML 2026 · similarity 0.88)
- A Selective Re-learning Mechanism for Hyperspectral Fusion Imaging (CVPR 2025 · similarity 0.87)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.86)
- Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion (NeurIPS 2024 · 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.
