Translator Disclaimer
Paper
1 June 2020 Deep neural network for joint light field deblurring and super-resolution
Author Affiliations +
Proceedings Volume 11515, International Workshop on Advanced Imaging Technology (IWAIT) 2020; 1151507 (2020) https://doi.org/10.1117/12.2566962
Event: International Workshop on Advanced Imaging Technologies 2020 (IWAIT 2020), 2020, Yogyakarta, Indonesia
Abstract
The recent works on the light field (LF) image enhancement are focused on specific tasks such as motion deblurring and super-resolution. State-of-the-art methods are limited with the specific case of 3-degree-of-freedom (3-DOF) camera motion (for motion deblurring) and straight-forward high-resolution neural network (for super-resolution (SR)). In this work, we proposed a framework that utilizes the deep neural net to solve LF spatial super- resolution and deblurring under 6-DOF camera motion. The neural network is designed with end-to-end fashion and trained in multiple stages to perform robust super-resolution and deblurring. Our neural network achieves superior results in terms of quantitative and qualitative performance compared to the recent state-of-the-art LF deblurring and SR algorithms.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jonathan Samuel Lumentut and In Kyu Park "Deep neural network for joint light field deblurring and super-resolution", Proc. SPIE 11515, International Workshop on Advanced Imaging Technology (IWAIT) 2020, 1151507 (1 June 2020); https://doi.org/10.1117/12.2566962
PROCEEDINGS
5 PAGES


SHARE
Advertisement
Advertisement
Back to Top