Abstract
Recent progress in spectral reconstruction from RGB images with deep learning seems promising for snapshot hyperspectral imaging. However, we show that significant limitations do exist arising from the lack of diversity in the prevailing datasets.
| Original language | English (US) |
|---|---|
| DOIs | |
| State | Published - 2024 |
| Event | Computational Optical Sensing and Imaging, COSI 2024 - Part of Optica Imaging Congress - Toulouse, France Duration: Jul 15 2024 → Jul 19 2024 |
Conference
| Conference | Computational Optical Sensing and Imaging, COSI 2024 - Part of Optica Imaging Congress |
|---|---|
| Country/Territory | France |
| City | Toulouse |
| Period | 07/15/24 → 07/19/24 |
Bibliographical note
Publisher Copyright:© 2024 The Author(s).
ASJC Scopus subject areas
- Control and Systems Engineering
- Electrical and Electronic Engineering
- Electronic, Optical and Magnetic Materials
- Instrumentation
- Atomic and Molecular Physics, and Optics
- General Computer Science
- Space and Planetary Science