Deep demosaicking for multispectral filter arrays

TL;DR

This paper introduces a deep learning-based demosaicking technique for multispectral filter arrays that improves image reconstruction quality over traditional methods.

Contribution

It presents a novel deep convolutional neural network architecture combining bilinear interpolation and residual learning for enhanced multispectral image demosaicking.

Findings

Outperforms conventional demosaicking methods

Uses 3D convolutional layers for feature extraction

Achieves higher reconstruction accuracy

Abstract

We propose a novel demosaicking method for multispectral filter arrays based on a deep convolutional neural network. The proposed method first interpolates mosaicked multispectral images utilizing a bilinear approach, then applies a residual network to initial demosaicked images. The residual network consists of various three-dimensional convolutional layers and a rectified linear unit for describing the features of a multispectral data cube. Experimental results reveal that the proposed method outperforms conventional demosaicking methods.