# An efficient CNN for spectral reconstruction from RGB images

arXiv: https://arxiv.org/abs/1804.04647 · HTML: https://mlsanity.com/paper/1804.04647/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2018.

## Built on by (most cited first, 5 of 5)

- [A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging](https://mlsanity.com/paper/2106.15944/) (2021)
- [Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Clues](https://mlsanity.com/paper/2312.11119/) (2023)
- [ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2502.16890/) (2025)
- [Tuning IR-cut Filter for Illumination-aware Spectral Reconstruction from RGB](https://mlsanity.com/paper/2103.14708/) (2021)
- [Inter and Intra Prior Learning-based Hyperspectral Image Reconstruction Using Snapshot SWIR Metasurface](https://mlsanity.com/paper/2407.07503/) (2024)

## Abstract (arXiv)

Recently, the example-based single image spectral reconstruction from RGB images task, aka, spectral super-resolution was approached by means of deep learning by Galliani et al. The proposed very deep convolutional neural network (CNN) achieved superior performance on recent large benchmarks. However, Aeschbacher et al showed that comparable performance can be achieved by shallow learning method based on A+, a method introduced for image super-resolution by Timofte et al. In this paper, we propose a moderately deep CNN model and substantially improve the reported performance on three spectral reconstruction standard benchmarks: ICVL, CAVE, and NUS.