Demosaiced Image via DCNN

One of the most important early stages in digital camera pipelines – addressed the problem of reconstructing a full-resolution image from so-called color-filter-arrays. Despite tremendous progress made in the past decade, a fundamental issue that remains to be addressed is how to assure the visual quality of reconstructed images especially in the presence of noise corruption.  Inspired by recent advances in generative adversarial networks, we present a novel deep learning approach toward joint demosaicing and denoising (JDD) with end-to-end optimization in order to ensure the visual quality of reconstructed images. Our experimental results have shown convincingly improved performance over existing state-of-the-art methods in terms of both subjective and objective quality metrics with a comparable computational cost. What is shown below is a demosaiced image from raw Bayer pattern sent back from NASA Mars curiosity.