Research map / Image generation / Super-resolution
Hyperspectral Image Super-Resolution via Non-Local Sparse Tensor Factorization
Check 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 NLSTF instead of the strongest reported baseline | HSI super-resolution · CAVE database | RMSE: 4.38 -> 2.60 | Helped |
| Use NLSTF instead of the strongest reported baseline | HSI super-resolution · CAVE database | SAM: 12.23 -> 6.83 | Helped |
| Use NLSTF instead of the strongest reported baseline | HSI super-resolution · Harvard database | RMSE: 2.46 -> 1.78 | Helped |
| Add non-local clustering of similar cubes (ablation) | STF · CAVE, Ballons | RMSE: 1.5 -> 1.3 | Helped |
| Add non-local clustering of similar cubes (ablation) | STF · CAVE, Beads | RMSE: 6.9 -> 5.5 | Helped |
| Add non-local clustering of similar cubes (ablation) | STF · CAVE, Cloth | RMSE: 4.6 -> 3.7 | Helped |
| Add non-local clustering of similar cubes (ablation) | STF · CAVE, Pompoms | RMSE: 2.5 -> 2.5 | No clear effect |
| Add non-local clustering of similar cubes (ablation) | STF · CAVE, CD | RMSE: 6.4 -> 5.3 | Helped |
| Use sparse tensor factorization rather than sparse matrix factorization | HSI super-resolution · CAVE, five images in Table 3 | RMSE: SMF -> STF: Ballons 2.3 -> 1.5; Beads 8.2 -> 6.9; Cloth 6.0 -> 4.6; Pompoms 4.3 -> 2.5; CD 7.9 -> 6.4 | Mixed |
Closest papers by meaning
- S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.89)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.89)
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.88)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.87)
- Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder Super-resolution Network (AAAI 2024 · similarity 0.86)
- MFTN: A Multi-scale Feature Transfer Network Based on IMatchFormer for Hyperspectral Image Super-Resolution (ICML 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.