Deep Demosaicing using ResNet-Bottleneck Architecture

EasyChair Preprint 1968

Abstract

Demosaicing is a fundamental step in a camera pipeline to construct a full RGB image from the bayer data captured by a camera sensor. The conventional signal processing algorithms fail to perform well on complex-pattern images giving rise to several artefacts like Moire, color and Zipper artefacts. The proposed deep learning based model removes such artefacts and generates visually superior quality images. The model performs well on both the sRGB (standard RGB color space) and the linear datasets without any need of retraining. It is based on Convolutional Neural Networks (CNNs) and uses a residual architecture with multiple `Residual Bottleneck Blocks' each having 3 CNN layers. The use of 1x1 kernels allowed to increase the number of filters (width) of the model and hence, learned the inter-channel dependencies in a better way. The proposed network outperforms the state-of-the-art demosaicing methods on both sRGB and linear datasets.

Keyphrases: Bayer image, CNN, Convolutional Layer, Demosaicing, Moire artefacts, RGB, Residual Bottleneck architecture, bottleneck architecture, color filter array, deep learning, image processing

@booklet{EasyChair:1968,
  author    = {Divakar Verma and Manish Kumar and Srinivas Eregala},
  title     = {Deep Demosaicing using ResNet-Bottleneck Architecture},
  howpublished = {EasyChair Preprint 1968},
  year      = {EasyChair, 2019}}