Abstract
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 ArticleMore Like This
Casey J. PeUizzari, Mark F. Spencer, and Charles A. Bouman
MTu4D.4 Mathematics in Imaging (MATH) 2019
Mohammad Haft-Javaherian, Chris B. Schaffer, Nozomi Nishimura, and Mert R. Sabuncu
BT2A.4 Optics and the Brain (BRAIN) 2019
Tomi Pitkäaho, Aki Manninen, and Thomas J. Naughton
Th3A.1 Digital Holography and Three-Dimensional Imaging (DH) 2019