Deep-Learning-Based Dynamic Range Compression for 3D Scene Hologram

Autor:	Peter Schelkens, Yota Yamamoto, Atsushi Shiraki, Tomoyoshi Ito, Tomoyoshi Shimobaba, Ikuo Hoshi, David Blinder, Takashi Kakue
Přispěvatelé:	Singh, Kehar, Gupta, A. K., Khare, Sudhir, Dixit, Nimish, Pant, Kamal, Multidimensional signal processing and communication, Electronics and Informatics
Jazyk:	angličtina
Rok vydání:	2021
Předmět:	Artificial neural network Computer science business.industry Deep learning Holography Binary number computer.file_format Stereo display law.invention law JPEG 2000 Gradation Dynamic range compression Computer vision Artificial intelligence business computer
Zdroj:	Springer Proceedings in Physics ISBN: 9789811592584
Popis:	This study proposes a dynamic-range compression for digital holograms generated from three-dimensional scenes using deep neural network (DNN). This method uses an error diffusion algorithm to binarize holograms with an 8-bit gradation; moreover, the DNN predicts the original gradation holograms from binary holograms. This method’s performance exceeds that of JPEG 2000 and high-efficiency video coding.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5750a3d5d283e70e270a9e65e0fcb8b2 https://hdl.handle.net/20.500.14017/fa5e8917-cd08-4246-bb93-d5a888299ff8 Zobrazit plný text záznamu