Channel-by-Channel Demosaicking Networks with Embedded Spectral Correlation
This work addresses the need for high-quality and low-cost demosaicking in photography and machine vision tasks, representing an incremental improvement over existing methods.
The paper tackles the problem of demosaicking in digital cameras by proposing a CNN-based model that reconstructs each color channel individually and uses color difference estimation to simplify the most complex channel. The result is a significantly smaller model that achieves higher performance in both demosaicking quality and computational cost compared to state-of-the-art networks.
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.