We explore the benefits of perceptual loss for light field (LF) spatial recon struction in a high-dimensional convolutional neural network. The results outperform some state-of-the-art methods for LF or image super-resolution.

© 2019 The Author(s)

PDF Article
More Like This
Comparison of convolutional neural and fully convolutional networks for segmentation of 3D in vivo multiphoton microscopy images of brain vasculature

Mohammad Haft-Javaherian, Chris B. Schaffer, Nozomi Nishimura, and Mert R. Sabuncu
BT2A.4 Optics and the Brain (BRAIN) 2019

Coherent-Image Reconstruction Using Convolutional Neural Networks

Casey J. PeUizzari, Mark F. Spencer, and Charles A. Bouman
MTu4D.4 Mathematics in Imaging (MATH) 2019

Digital hologram reconstruction segmentation using a convolutional neural network

Tomi Pitkäaho, Aki Manninen, and Thomas J. Naughton
Th3A.1 Digital Holography and Three-Dimensional Imaging (DH) 2019


You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
Login to access OSA Member Subscription