Comparative verification of 3D reconstructed point cloud data: comparison of AI estimation and multi-view stereo methods using Nerfstudio and Metashape

We investigated the feasibility of using a 3D point cloud estimated by a neural radiance field (NeRF). We evaluated the quality of point clouds reconstructed with NeRF and multi-view stereo. The point cloud reconstructed by NeRF contains substantial noise and shows a wavy surface even on a flat surf...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuta Tsukamoto, Atsushi Hayashi, Kenichi Tokuda, Nobuo Kochi
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:SICE Journal of Control, Measurement, and System Integration
Subjects:
Online Access:http://dx.doi.org/10.1080/18824889.2025.2497600
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850273669960433664
author Yuta Tsukamoto
Atsushi Hayashi
Kenichi Tokuda
Nobuo Kochi
author_facet Yuta Tsukamoto
Atsushi Hayashi
Kenichi Tokuda
Nobuo Kochi
author_sort Yuta Tsukamoto
collection DOAJ
description We investigated the feasibility of using a 3D point cloud estimated by a neural radiance field (NeRF). We evaluated the quality of point clouds reconstructed with NeRF and multi-view stereo. The point cloud reconstructed by NeRF contains substantial noise and shows a wavy surface even on a flat surface. Therefore, a point cloud generated by NeRF is not appropriate as a highly accurate 3D model with the size and shape of an actual object. However, it is effective for applications that do not require highly accurate point clouds, such as the detection and 3D modelling of objects with few feature-point surfaces or optically transparent objects, which have been difficult to achieve using conventional methods.
format Article
id doaj-art-ff0c4bb6eb2d41e892f452e6b4cb638f
institution OA Journals
issn 1884-9970
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series SICE Journal of Control, Measurement, and System Integration
spelling doaj-art-ff0c4bb6eb2d41e892f452e6b4cb638f2025-08-20T01:51:24ZengTaylor & Francis GroupSICE Journal of Control, Measurement, and System Integration1884-99702025-12-0118110.1080/18824889.2025.24976002497600Comparative verification of 3D reconstructed point cloud data: comparison of AI estimation and multi-view stereo methods using Nerfstudio and MetashapeYuta Tsukamoto0Atsushi Hayashi1Kenichi Tokuda2Nobuo Kochi3Institute of Science TokyoNational Agriculture and Food Research OrganizationNational Agriculture and Food Research OrganizationNational Agriculture and Food Research OrganizationWe investigated the feasibility of using a 3D point cloud estimated by a neural radiance field (NeRF). We evaluated the quality of point clouds reconstructed with NeRF and multi-view stereo. The point cloud reconstructed by NeRF contains substantial noise and shows a wavy surface even on a flat surface. Therefore, a point cloud generated by NeRF is not appropriate as a highly accurate 3D model with the size and shape of an actual object. However, it is effective for applications that do not require highly accurate point clouds, such as the detection and 3D modelling of objects with few feature-point surfaces or optically transparent objects, which have been difficult to achieve using conventional methods.http://dx.doi.org/10.1080/18824889.2025.24976003d reconstructionnerfmulti-view stereophotogrammetrypoint cloud
spellingShingle Yuta Tsukamoto
Atsushi Hayashi
Kenichi Tokuda
Nobuo Kochi
Comparative verification of 3D reconstructed point cloud data: comparison of AI estimation and multi-view stereo methods using Nerfstudio and Metashape
SICE Journal of Control, Measurement, and System Integration
3d reconstruction
nerf
multi-view stereo
photogrammetry
point cloud
title Comparative verification of 3D reconstructed point cloud data: comparison of AI estimation and multi-view stereo methods using Nerfstudio and Metashape
title_full Comparative verification of 3D reconstructed point cloud data: comparison of AI estimation and multi-view stereo methods using Nerfstudio and Metashape
title_fullStr Comparative verification of 3D reconstructed point cloud data: comparison of AI estimation and multi-view stereo methods using Nerfstudio and Metashape
title_full_unstemmed Comparative verification of 3D reconstructed point cloud data: comparison of AI estimation and multi-view stereo methods using Nerfstudio and Metashape
title_short Comparative verification of 3D reconstructed point cloud data: comparison of AI estimation and multi-view stereo methods using Nerfstudio and Metashape
title_sort comparative verification of 3d reconstructed point cloud data comparison of ai estimation and multi view stereo methods using nerfstudio and metashape
topic 3d reconstruction
nerf
multi-view stereo
photogrammetry
point cloud
url http://dx.doi.org/10.1080/18824889.2025.2497600
work_keys_str_mv AT yutatsukamoto comparativeverificationof3dreconstructedpointclouddatacomparisonofaiestimationandmultiviewstereomethodsusingnerfstudioandmetashape
AT atsushihayashi comparativeverificationof3dreconstructedpointclouddatacomparisonofaiestimationandmultiviewstereomethodsusingnerfstudioandmetashape
AT kenichitokuda comparativeverificationof3dreconstructedpointclouddatacomparisonofaiestimationandmultiviewstereomethodsusingnerfstudioandmetashape
AT nobuokochi comparativeverificationof3dreconstructedpointclouddatacomparisonofaiestimationandmultiviewstereomethodsusingnerfstudioandmetashape