In this paper, we present a single view focal plane reconstruction by using deep learning in integral imaging system. To synthesize multi-views from single view, a learning-based method is used to generate depth information and render a Lambertian approximation based on a physically-based warping layer. Then we use the synthesized multi-view images to reconstruct focal plane. The experimental results show that the significant superiority of the proposed method.

© 2019 The Author(s)

PDF Article


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