An efficient CNN for spectral reconstruction from RGB images

Abstract

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.

arXiv commentSubmitted to ICIP 2018

Cited by in corpus (8)

• Spectral Superresolution of Multispectral Imagery with Joint Sparse and Low-Rank Learning
• AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Images
• Light Weight Residual Dense Attention Net for Spectral Reconstruction from RGB Images
• MXR-U-Nets for Real Time Hyperspectral Reconstruction
• Hierarchical Regression Network for Spectral Reconstruction from RGB Images
• Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolution
• NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image
• Tuning IR-cut Filter for Illumination-aware Spectral Reconstruction from RGB