Image Colorization By Capsule Networks

Ozbulak G.

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), California, United States Of America, 16 - 20 June 2019, pp.2150-2158 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/cvprw.2019.00268
  • City: California
  • Country: United States Of America
  • Page Numbers: pp.2150-2158
  • Istanbul Technical University Affiliated: Yes


In this paper, a simple topology of Capsule Network (CapsNet) is investigatedfor the problem of image colorization. The generative and segmentation capabilities of the original CapsNet topology, which is proposed for image classification problem, is leveraged for the colorization of the images by modifying the network as follows: I) The original CapsNet model is adapted to map the grayscale input to the output in the CIE Lab colorspace, 2) The feature detector part of the model is updated by using deeper feature layers inherited from VGG-19 pre-trained model with weights in order to transfer low-level image representation capability to this model, 3) The margin loss function is modified as Mean Squared Error (MSE) loss to minimize the image-to-image mapping. The resulting CapsNet model is named as Colorizer Capsule Network (ColorCapsNet). The performance of the ColorCapsNet is evaluated on the DIV2K dataset and promising results are obtained to investigate Capsule Networks further for image colorization problem.