TY - GEN
T1 - Fast and accurate reconstruction of compressed color light field
AU - Nabati, Ofir
AU - Mendlovic, David
AU - Giryes, Raja
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/5/29
Y1 - 2018/5/29
N2 - Light field photography has been studied thoroughly in recent years. One of its drawbacks is the need for multi-lens in the imaging. To compensate that, compressed light field photography has been proposed to tackle the trade-offs between the spatial and angular resolutions. It obtains by only one lens, a compressed version of the regular multi-lens system. The acquisition system consists of a dedicated hardware followed by a decompression algorithm, which usually suffers from high computational time. In this work, we propose a computationally efficient neural network that recovers a high-quality color light field from a single coded image. Unlike previous works, we compress the color channels as well, removing the need for a CFA in the imaging system. Our approach outperforms existing solutions in terms of recovery quality and computational complexity. We propose also a neural network for depth map extraction based on the decompressed light field, which is trained in an unsupervised manner without the ground truth depth map.
AB - Light field photography has been studied thoroughly in recent years. One of its drawbacks is the need for multi-lens in the imaging. To compensate that, compressed light field photography has been proposed to tackle the trade-offs between the spatial and angular resolutions. It obtains by only one lens, a compressed version of the regular multi-lens system. The acquisition system consists of a dedicated hardware followed by a decompression algorithm, which usually suffers from high computational time. In this work, we propose a computationally efficient neural network that recovers a high-quality color light field from a single coded image. Unlike previous works, we compress the color channels as well, removing the need for a CFA in the imaging system. Our approach outperforms existing solutions in terms of recovery quality and computational complexity. We propose also a neural network for depth map extraction based on the decompressed light field, which is trained in an unsupervised manner without the ground truth depth map.
UR - http://www.scopus.com/inward/record.url?scp=85048885121&partnerID=8YFLogxK
U2 - 10.1109/ICCPHOT.2018.8368477
DO - 10.1109/ICCPHOT.2018.8368477
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85048885121
T3 - IEEE International Conference on Computational Photography, ICCP 2018
SP - 1
EP - 11
BT - IEEE International Conference on Computational Photography, ICCP 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Computational Photography, ICCP 2018
Y2 - 4 May 2018 through 6 May 2018
ER -