DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes

This paper presents an accurate and robust dense 3D reconstruction system for detail preserving surface modeling of large-scale scenes from multi-view images, which we named DP-MVS. Our system performs high-quality large-scale dense reconstruction, which preserves geometric details for thin structur...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Liyang Zhou, Zhuang Zhang, Hanqing Jiang, Han Sun, Hujun Bao, Guofeng Zhang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	multi-view reconstruction detail preserving depth estimation surface meshing Science Q
Acceso en línea:	https://doaj.org/article/12aa9427d272436faf18d5ca457a7c29
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:12aa9427d272436faf18d5ca457a7c29
record_format	dspace
spelling	oai:doaj.org-article:12aa9427d272436faf18d5ca457a7c292021-11-25T18:54:27ZDP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes10.3390/rs132245692072-4292https://doaj.org/article/12aa9427d272436faf18d5ca457a7c292021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4569https://doaj.org/toc/2072-4292This paper presents an accurate and robust dense 3D reconstruction system for detail preserving surface modeling of large-scale scenes from multi-view images, which we named DP-MVS. Our system performs high-quality large-scale dense reconstruction, which preserves geometric details for thin structures, especially for linear objects. Our framework begins with a sparse reconstruction carried out by an incremental Structure-from-Motion. Based on the reconstructed sparse map, a novel detail preserving PatchMatch approach is applied for depth estimation of each image view. The estimated depth maps of multiple views are then fused to a dense point cloud in a memory-efficient way, followed by a detail-aware surface meshing method to extract the final surface mesh of the captured scene. Experiments on ETH3D benchmark show that the proposed method outperforms other state-of-the-art methods on F1-score, with the running time more than 4 times faster. More experiments on large-scale photo collections demonstrate the effectiveness of the proposed framework for large-scale scene reconstruction in terms of accuracy, completeness, memory saving, and time efficiency.Liyang ZhouZhuang ZhangHanqing JiangHan SunHujun BaoGuofeng ZhangMDPI AGarticlemulti-view reconstructiondetail preservingdepth estimationsurface meshingScienceQENRemote Sensing, Vol 13, Iss 4569, p 4569 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	multi-view reconstruction detail preserving depth estimation surface meshing Science Q
spellingShingle	multi-view reconstruction detail preserving depth estimation surface meshing Science Q Liyang Zhou Zhuang Zhang Hanqing Jiang Han Sun Hujun Bao Guofeng Zhang DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes
description	This paper presents an accurate and robust dense 3D reconstruction system for detail preserving surface modeling of large-scale scenes from multi-view images, which we named DP-MVS. Our system performs high-quality large-scale dense reconstruction, which preserves geometric details for thin structures, especially for linear objects. Our framework begins with a sparse reconstruction carried out by an incremental Structure-from-Motion. Based on the reconstructed sparse map, a novel detail preserving PatchMatch approach is applied for depth estimation of each image view. The estimated depth maps of multiple views are then fused to a dense point cloud in a memory-efficient way, followed by a detail-aware surface meshing method to extract the final surface mesh of the captured scene. Experiments on ETH3D benchmark show that the proposed method outperforms other state-of-the-art methods on F1-score, with the running time more than 4 times faster. More experiments on large-scale photo collections demonstrate the effectiveness of the proposed framework for large-scale scene reconstruction in terms of accuracy, completeness, memory saving, and time efficiency.
format	article
author	Liyang Zhou Zhuang Zhang Hanqing Jiang Han Sun Hujun Bao Guofeng Zhang
author_facet	Liyang Zhou Zhuang Zhang Hanqing Jiang Han Sun Hujun Bao Guofeng Zhang
author_sort	Liyang Zhou
title	DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes
title_short	DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes
title_full	DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes
title_fullStr	DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes
title_full_unstemmed	DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes
title_sort	dp-mvs: detail preserving multi-view surface reconstruction of large-scale scenes
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/12aa9427d272436faf18d5ca457a7c29
work_keys_str_mv	AT liyangzhou dpmvsdetailpreservingmultiviewsurfacereconstructionoflargescalescenes AT zhuangzhang dpmvsdetailpreservingmultiviewsurfacereconstructionoflargescalescenes AT hanqingjiang dpmvsdetailpreservingmultiviewsurfacereconstructionoflargescalescenes AT hansun dpmvsdetailpreservingmultiviewsurfacereconstructionoflargescalescenes AT hujunbao dpmvsdetailpreservingmultiviewsurfacereconstructionoflargescalescenes AT guofengzhang dpmvsdetailpreservingmultiviewsurfacereconstructionoflargescalescenes
_version_	1718410571387240448

DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes

Ejemplares similares