Cargando…

Fast and Accurate Light Field View Synthesis by Optimizing Input View Selection

There is a trade-off between spatial resolution and angular resolution limits in light field applications; various targeted algorithms have been proposed to enhance angular resolution while ensuring high spatial resolution simultaneously, which is also called view synthesis. Among them, depth estima...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Xingzheng, Zan, Yongqiang, You, Senlin, Deng, Yuanlong, Li, Lihua
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8153318/
https://www.ncbi.nlm.nih.gov/pubmed/34068327
http://dx.doi.org/10.3390/mi12050557
_version_ 1783698774384705536
author Wang, Xingzheng
Zan, Yongqiang
You, Senlin
Deng, Yuanlong
Li, Lihua
author_facet Wang, Xingzheng
Zan, Yongqiang
You, Senlin
Deng, Yuanlong
Li, Lihua
author_sort Wang, Xingzheng
collection PubMed
description There is a trade-off between spatial resolution and angular resolution limits in light field applications; various targeted algorithms have been proposed to enhance angular resolution while ensuring high spatial resolution simultaneously, which is also called view synthesis. Among them, depth estimation-based methods can use only four corner views to reconstruct a novel view at an arbitrary location. However, depth estimation is a time-consuming process, and the quality of the reconstructed novel view is not only related to the number of the input views, but also the location of the input views. In this paper, we explore the relationship between different input view selections with the angular super-resolution reconstruction results. Different numbers and positions of input views are selected to compare the speed of super-resolution reconstruction and the quality of novel views. Experimental results show that the speed of the algorithm decreases with the increase of the input views for each novel view, and the quality of the novel view decreases with the increase of the distance from the input views. After comparison using two input views in the same line to reconstruct the novel views between them, fast and accurate light field view synthesis is achieved.
format Online
Article
Text
id pubmed-8153318
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-81533182021-05-27 Fast and Accurate Light Field View Synthesis by Optimizing Input View Selection Wang, Xingzheng Zan, Yongqiang You, Senlin Deng, Yuanlong Li, Lihua Micromachines (Basel) Article There is a trade-off between spatial resolution and angular resolution limits in light field applications; various targeted algorithms have been proposed to enhance angular resolution while ensuring high spatial resolution simultaneously, which is also called view synthesis. Among them, depth estimation-based methods can use only four corner views to reconstruct a novel view at an arbitrary location. However, depth estimation is a time-consuming process, and the quality of the reconstructed novel view is not only related to the number of the input views, but also the location of the input views. In this paper, we explore the relationship between different input view selections with the angular super-resolution reconstruction results. Different numbers and positions of input views are selected to compare the speed of super-resolution reconstruction and the quality of novel views. Experimental results show that the speed of the algorithm decreases with the increase of the input views for each novel view, and the quality of the novel view decreases with the increase of the distance from the input views. After comparison using two input views in the same line to reconstruct the novel views between them, fast and accurate light field view synthesis is achieved. MDPI 2021-05-13 /pmc/articles/PMC8153318/ /pubmed/34068327 http://dx.doi.org/10.3390/mi12050557 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Xingzheng
Zan, Yongqiang
You, Senlin
Deng, Yuanlong
Li, Lihua
Fast and Accurate Light Field View Synthesis by Optimizing Input View Selection
title Fast and Accurate Light Field View Synthesis by Optimizing Input View Selection
title_full Fast and Accurate Light Field View Synthesis by Optimizing Input View Selection
title_fullStr Fast and Accurate Light Field View Synthesis by Optimizing Input View Selection
title_full_unstemmed Fast and Accurate Light Field View Synthesis by Optimizing Input View Selection
title_short Fast and Accurate Light Field View Synthesis by Optimizing Input View Selection
title_sort fast and accurate light field view synthesis by optimizing input view selection
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8153318/
https://www.ncbi.nlm.nih.gov/pubmed/34068327
http://dx.doi.org/10.3390/mi12050557
work_keys_str_mv AT wangxingzheng fastandaccuratelightfieldviewsynthesisbyoptimizinginputviewselection
AT zanyongqiang fastandaccuratelightfieldviewsynthesisbyoptimizinginputviewselection
AT yousenlin fastandaccuratelightfieldviewsynthesisbyoptimizinginputviewselection
AT dengyuanlong fastandaccuratelightfieldviewsynthesisbyoptimizinginputviewselection
AT lilihua fastandaccuratelightfieldviewsynthesisbyoptimizinginputviewselection