Research map / 3D vision / Depth and stereo
Deeply Learned Filter Response Functions for Hyperspectral Reconstruction
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 |
|---|---|---|---|
| Learn task-optimized filter responses jointly with the reconstruction mapping instead of using standard RGB camera responses | Three-chip hyperspectral reconstruction · CAVE | RMSE: 8.84 -> 4.48 | Helped |
| Learn task-optimized filter responses jointly with the reconstruction mapping instead of using standard RGB camera responses | Three-chip hyperspectral reconstruction · Harvard Natural | RMSE: 9.06 -> 7.57 | Helped |
| Learn task-optimized filter responses jointly with the reconstruction mapping instead of using standard RGB camera responses | Three-chip hyperspectral reconstruction · Harvard Mixed | RMSE: 9.74 -> 8.88 | Helped |
| Use learned Bayer-style 2×2 filter responses instead of standard RGB responses | Single-chip hyperspectral reconstruction · CAVE | RMSE: 13.25 -> 4.73 | Helped |
| Use two channels instead of three (ablation) | Learned-filter multispectral camera · CAVE | RMSE: 4.48 -> 5.76 | Hurt |
Closest papers by meaning
- Tuning IR-Cut Filter for Illumination-Aware Spectral Reconstruction From RGB (CVPR 2021 · similarity 0.90)
- A General Filter-Enhanced Approach to Smartphone Hyperspectral Imaging (NeurIPS 2026 · similarity 0.89)
- Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Clues (AAAI 2024 · similarity 0.87)
- FRN: Fractal-Based Recursive Spectral Reconstruction Network (NeurIPS 2025 · similarity 0.86)
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction (CVPR 2024 · similarity 0.86)
- A Selective Re-learning Mechanism for Hyperspectral Fusion Imaging (CVPR 2025 · similarity 0.85)
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.