Channel-by-Channel Demosaicking Networks with Embedded Spectral Correlation

Demosaicking is standardly the first step in today's Image Signal Processing (ISP) pipeline of digital cameras. It reconstructs image RGB values from the spatially and spectrally sparse Color Filter Array (CFA) samples, which are the original raw data digitized from electrical signals. High quality and low cost demosaicking is not only necessary for photography, but also fundamental for many machine vision tasks. This paper proposes an accurate and fast demosaicking model based on Convolutional Neural Networks (CNN) for the Bayer CFA, which is the most popular color filter arrangement adopted by digital camera manufacturers. Observing that each channel has different estimation complexity, we reconstruct each channel by an individual sub-network. Moreover, instead of directly estimating the red and blue values, our model infers the green-red and green-blue color difference. This strategy allows recovering the most complex channel by a light weight network. Although the total size of our model is significantly smaller than the state of the art demosaicking networks, it achieves substantially higher performance in both demosaicking quality and computational cost, as validated by extensive experiments. Source code will be released along with paper publication.