Research map / 3D vision / Depth and stereo
Catadioptric HyperSpectral Light Field Imaging
Yujia Xue, Kang Zhu, Qiang Fu, Xilin Chen, Jingyi Yu
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 |
|---|---|---|---|
| recover depth with cross-spectrum RSNCC plus refocus energy instead of SSD or NCC stereo matching | SPI depth estimation · Simulated and real hyperspectral light fields | depth map quality | Improved |
| recover spectra toward the band edges (400nm, 700nm) versus mid-band | SPI spectral reconstruction · Simulated SPI, Columbia hyperspectral scenes | band-wise RMSE: 28.1 vs 1.4 | Hurt |
| reduce sensor quantum efficiency outside 420-680nm | SPI spectral reconstruction · Simulated SPI, Columbia hyperspectral scenes | band-wise RMSE | Hurt |
Closest papers by meaning
- Snapshot Hyperspectral Light Field Imaging (CVPR 2017 · similarity 0.91)
- Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion (ECCV 2026 · similarity 0.88)
- Spectral Compressive Imaging via Chromaticity-Intensity Decomposition (NeurIPS 2025 · similarity 0.86)
- Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification (CVPR 2024 · similarity 0.85)
- Dense Dispersed Structured Light for Hyperspectral 3D Imaging of Dynamic Scenes (CVPR 2025 · similarity 0.84)
- SPECAT: SPatial-spEctral Cumulative-Attention Transformer for High-Resolution Hyperspectral Image Reconstruction (CVPR 2024 · similarity 0.84)
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.
