DeepDemosaicking: Adaptive Image Demosaicking via Multiple Deep Fully Convolutional Networks

Daniel Stanley Tan, Wei-Yang Chen, Kai-Lung Hua

Research output: Contribution to journalArticleAcademicpeer-review


Convolutional neural networks are currently the state-of-the-art solution for a wide range of image processing tasks. Their deep architecture extracts low- and high-level features from images, thus improving the model's performance. In this paper, we propose a method for image demosaicking based on deep convolutional neural networks. Demosaicking is the task of reproducing full color images from incomplete images formed from overlaid color filter arrays on image sensors found in digital cameras. Instead of producing the output image directly, the proposed method divides the demosaicking task into an initial demosaicking step and a refinement step. The initial step produces a rough demosaicked image containing unwanted color artifacts. The refinement step then reduces these color artifacts using deep residual estimation and multi-model fusion producing a higher quality image. Experimental results show that the proposed method outperforms several existing and state-of-the-art methods in terms of both the subjective and objective evaluations.
Original languageEnglish
Pages (from-to)2408 - 2419
Number of pages11
JournalIeee Transactions on Image Processing
Issue number5
Publication statusPublished - May 2018
Externally publishedYes


  • Image demosaicking
  • deep convolutional networks
  • multi-model fusion


Dive into the research topics of 'DeepDemosaicking: Adaptive Image Demosaicking via Multiple Deep Fully Convolutional Networks'. Together they form a unique fingerprint.

Cite this