Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB

Abstract

Hyperspectral signal reconstruction aims at recovering the original spectral input that produced a certain trichromatic (RGB) response from a capturing device or observer. Given the heavily underconstrained, non-linear nature of the problem, traditional techniques leverage different statistical properties of the spectral signal in order to build informative priors from real world object reflectances for constructing such RGB to spectral signal mapping. However, most of them treat each sample independently, and thus do not benefit from the contextual information that the spatial dimensions can provide. We pose hyperspectral natural image reconstruction as an image to image mapping learning problem, and apply a conditional generative adversarial framework to help capture spatial semantics. This is the first time Convolutional Neural Networks -and, particularly, Generative Adversarial Networks- are used to solve this task. Quantitative evaluation shows a Root Mean Squared Error (RMSE) drop of 33.2% and a Relative RMSE drop of 54.0% on the ICVL natural hyperspectral image dataset.

Accepted at IEEE ICCVW 2017 - "Physics Based Vision meets Deep Learning" Workshop (PBDL 2017). Added train-test splits and updated results

References in corpus (13)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Generative Adversarial Text to Image Synthesis
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Improved Techniques for Training GANs
• Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
• A note on the evaluation of generative models
• Learning What and Where to Draw
• Learned Spectral Super-Resolution
• PixelNet: Representation of the pixels, by the pixels, and for the pixels
• Instance-aware Semantic Segmentation via Multi-task Network Cascades
• Towards Adversarial Retinal Image Synthesis

Cited by in corpus (10)

• A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging
• $S^2$Net: Accurate Panorama Depth Estimation on Spherical Surface
• 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
• Pixel-aware Deep Function-mixture Network for Spectral Super-Resolution
• Learning to Recover Spectral Reflectance from RGB Images
• Quasi-spectral characterization of intracellular regions in bright-field light microscopy images
• Hyperspectral recovery from RGB images using Gaussian Processes
• Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Images
• Tuning IR-cut Filter for Illumination-aware Spectral Reconstruction from RGB