Research map / 3D vision / Depth and stereo
Filter Selection for Hyperspectral Estimation
Boaz Arad, Ohad Ben-Shahar
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 |
|---|---|---|---|
| select the best consumer camera filters instead of the worst | Arad and Ben-Shahar method · 28 consumer cameras | RRMSE: 0.160 -> 0.127 (20.6% improvement) | Improved |
| select the best consumer camera filters instead of the worst | Nguyen et al. method · 28 consumer cameras | RRMSE: 0.293 -> 0.238 (18.7% improvement) | Improved |
| use an optimal generic Midopt filter set instead of the best consumer camera | Arad and Ben-Shahar method · Midopt filter space | RRMSE: 0.127 -> 0.116 | Improved |
| combine filters from different cameras instead of one camera | Arad and Ben-Shahar method · commercial camera filter space | RRMSE: 0.127 -> 0.119 | Improved |
| use a large OMEGA filter space instead of the commercial camera filter space | Arad and Ben-Shahar method · OMEGA filter space | RRMSE: 0.119 -> 0.107 | Improved |
| use evolutionary optimization instead of exhaustive search | filter set selection · commercial camera filter space | evaluations needed: 95284 -> less than 13800 filter sets | Improved |
| use evolutionary optimization instead of random search | filter set selection · OMEGA filter space | evaluations to reach RRMSE 0.107: 344,600 -> 39,595 | Improved |
| evaluate filter sets on a 2.5 million pixel random subset instead of the full test set (ablation) | filter set selection · BGU HS database | RRMSE | No clear effect |
| use optimal custom filter set from OMEGA instead of consumer camera Olympus E-PL2 | Arad and Ben-Shahar method · BGU HS database | RRMSE reduction: at least 33.1% | Improved |
Closest papers by meaning
- Deeply Learned Filter Response Functions for Hyperspectral Reconstruction (CVPR 2018 · similarity 0.89)
- Joint Camera Spectral Response Selection and Hyperspectral Image Recovery (TPAMI 2020 · similarity 0.86)
- Do It Yourself Hyperspectral Imaging With Everyday Digital Cameras (CVPR 2016 · similarity 0.86)
- Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery (ECCV 2018 · similarity 0.86)
- HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery (CVPR 2025 · similarity 0.83)
- A Selective Re-learning Mechanism for Hyperspectral Fusion Imaging (CVPR 2025 · similarity 0.82)
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.
