Research map / Image generation / Super-resolution
Unaligned RGB Guided Hyperspectral Image Super-Resolution with Spatial-Spectral Concordance
Yingkai Zhang, Zeqiang Lai, Tao Zhang, Ying Fu, Chenghu Zhou
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 two-stage image alignment (OF+WarpNet) to UNet baseline (ablation) | UNet fusion baseline · Real x8 | PSNR: 31.48 -> 34.74 | Improved |
| add feature aggregation on top of TSIA (ablation) | SSC-HSR · Real x8 | PSNR: 34.74 -> 35.81 | Improved |
| add attention fusion on top of TSIA+FA (ablation) | SSC-HSR · Real x8 | PSNR: 35.81 -> 37.37 | Improved |
| add optical flow model before FA and AF (ablation) | SSC-HSR · Real x8 | PSNR: 36.66 -> 37.12 | Improved |
| add WarpNet after fine-tuned optical flow (ablation) | SSC-HSR · Real x8 | PSNR: 37.12 -> 37.37 | Improved |
| fine-tune RAFT on synthetic cross-resolution pipeline data and add WarpNet (ablation) | TSIA · Real x8 optical flow | EPE: 11.86 -> 1.77 | Improved |
| fine-tune RAFT and add WarpNet (warped reference quality) (ablation) | TSIA · Real x8 | PSNR: 26.17 -> 34.46 | Improved |
| add interaction between FA and fusion, 2 layers (ablation) | SSC-HSR · Real x8 | PSNR: 35.64 -> 37.19 | Improved |
| add interaction between FA and fusion, 3 layers (ablation) | SSC-HSR · Real x8 | PSNR: 37.25 -> 37.37 | Improved |
| replace UNet fusion with spectral self-attention (SSA) (ablation) | SSC-HSR · Real x8 | PSNR: 35.81 -> 36.06 | Improved |
| add reference-guided cross-attention to SSA (ablation) | SSC-HSR · Real x8 | PSNR: 36.06 -> 37.37 | Improved |
| increase number of levels from 1 to 2 (ablation) | SSC-HSR · Real x8 | PSNR: 35.16 -> 37.19 | Improved |
Closest papers by meaning
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.91)
- Hyperspectral Image Super-Resolution With Optimized RGB Guidance (CVPR 2019 · similarity 0.90)
- S2CycleDiff: Spatial-Spectral-Bilateral Cycle-Diffusion Framework for Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.89)
- Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution (AAAI 2024 · similarity 0.89)
- Automatic Spectral Calibration of Hyperspectral Images: Method, Dataset and Benchmark (CVPR 2025 · similarity 0.88)
- MFTN: A Multi-scale Feature Transfer Network Based on IMatchFormer for Hyperspectral Image Super-Resolution (ICML 2024 · similarity 0.87)
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.
