Research map / Image generation / Super-resolution
Unsupervised Sparse Dirichlet-Net for Hyperspectral Image Super-Resolution
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use uSDN instead of BSR | HSI-SR · CAVE | RMSE: 5.29 -> 4.09 | Helped |
| Use uSDN instead of BSR | HSI-SR · CAVE | SAM: 13.63 -> 6.95 | Helped |
| Use uSDN instead of BSR | HSI-SR · Harvard | RMSE: 2.61 -> 1.78 | Helped |
| Use uSDN instead of BSR | HSI-SR · Harvard | SAM: 4.46 -> 4.05 | Helped |
| Add Dirichlet-Net representation constraints (ablation) | HSI-SR on CAVE pompom · CAVE pompom | RMSE | Helped |
| Add sparsity constraint to Dirichlet-Net (ablation) | HSI-SR on CAVE pompom · CAVE pompom | RMSE | Helped |
| Use reconstruction loss together with angular similarity loss (ablation) | MSI network update on CAVE pompom · CAVE pompom | SAM | Helped |
| Add reconstruction loss to angular-similarity-only training (ablation) | MSI network update on CAVE pompom · CAVE pompom | convergence stability | Helped |
| Increase sparsity weight λ from 2×10⁻⁷ to 1×10⁻⁶ (ablation) | uSDN · CAVE pompom | RMSE | Helped |
Closest papers by meaning
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.91)
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.90)
- S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.89)
- MFTN: A Multi-scale Feature Transfer Network Based on IMatchFormer for Hyperspectral Image Super-Resolution (ICML 2024 · similarity 0.88)
- Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network (AAAI 2024 · similarity 0.88)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.88)
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.