• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Book chapter

Depth Map Interpolation using Perceptual Loss

P. 1-2.
Makarov I., Vladimir Aliev, Gerasimova Olga, Pavel Polyakov.

In this paper, we discuss a semi-dense  depth map interpolation method based on convolutional neural network. We propose a compact  neural network architecture with loss function defined as Euclidean distance in the feature space of VGG-16 neural network used for deep visual recognition. The suggested solution shows state-of-art performance on synthetic and real datasets. Together with LSD-SLAM, the method could be used to provide a dense depth map for interaction purposes, such as creating a first person game in AR/MR or perception module for autonomous vehicle.