Research map / Image generation / Image restoration
Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery
Ying Fu, Tao Zhang, Yinqiang Zheng, Debing Zhang, Hua Huang
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 |
|---|---|---|---|
| use the proposed spectral+spatial CNN recovery instead of manifold-based mapping (MM) | HSI recovery · ICVL | RMSE: 2.1245 -> 1.3533 | Improved |
| use the proposed CNN recovery instead of MM | HSI recovery · NUS | RMSE: 6.1825 -> 5.2426 | Improved |
| use the proposed CNN recovery instead of MM | HSI recovery · Harvard | RMSE: 4.9616 -> 2.1923 | Improved |
| use the proposed CNN recovery instead of MM | HSI recovery · ICVL | SAM: 0.0470 -> 0.0277 | Improved |
| use the proposed CNN recovery instead of MM | HSI recovery · Harvard | SAM: 0.2273 -> 0.0956 | Improved |
| use the proposed CNN recovery instead of MM | HSI recovery · NUS | SSIM: 0.9555 -> 0.9649 | Improved |
| run the proposed network on GPU instead of CPU | Ours · 256x256x31 HSI runtime | time (s): 18.94 -> 0.09 | Improved |
| proposed network versus MM on CPU runtime | Ours (CPU) · 256x256x31 HSI runtime | time (s): 4.13 -> 18.94 | Hurt |
| choose the optimal camera spectral sensitivity (CSS) with the selection layer instead of a fixed or worst CSS (ablation) | HSI recovery network · two CSS datasets (28 and 12 curves), three HSI datasets | RMSE | Improved |
Closest papers by meaning
- Joint Camera Spectral Response Selection and Hyperspectral Image Recovery (TPAMI 2020 · similarity 0.98)
- Hyperspectral Image Super-Resolution With Optimized RGB Guidance (CVPR 2019 · similarity 0.91)
- Spectrum-Aware and Transferable Architecture Search for Hyperspectral Image Restoration (ECCV 2022 · similarity 0.91)
- Hyperspectral Image Reconstruction Using Deep External and Internal Learning (ICCV 2019 · similarity 0.91)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.88)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 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.
