NeuralMeshing: Complete Object Mesh Extraction from Casual Captures

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Erich, Floris, Chiba, Naoya, Mustafa, Abdullah, Hanai, Ryo, Ando, Noriaki, Yoshiyasu, Yusuke, Domae, Yukiyasu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911116460818432
author Erich, Floris
Chiba, Naoya
Mustafa, Abdullah
Hanai, Ryo
Ando, Noriaki
Yoshiyasu, Yusuke
Domae, Yukiyasu
author_facet Erich, Floris
Chiba, Naoya
Mustafa, Abdullah
Hanai, Ryo
Ando, Noriaki
Yoshiyasu, Yusuke
Domae, Yukiyasu
contents How can we extract complete geometric models of objects that we encounter in our daily life, without having access to commercial 3D scanners? In this paper we present an automated system for generating geometric models of objects from two or more videos. Our system requires the specification of one known point in at least one frame of each video, which can be automatically determined using a fiducial marker such as a checkerboard or Augmented Reality (AR) marker. The remaining frames are automatically positioned in world space by using Structure-from-Motion techniques. By using multiple videos and merging results, a complete object mesh can be generated, without having to rely on hole filling. Code for our system is available from https://github.com/FlorisE/NeuralMeshing.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16026
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeuralMeshing: Complete Object Mesh Extraction from Casual Captures
Erich, Floris
Chiba, Naoya
Mustafa, Abdullah
Hanai, Ryo
Ando, Noriaki
Yoshiyasu, Yusuke
Domae, Yukiyasu
Computer Vision and Pattern Recognition
Robotics
How can we extract complete geometric models of objects that we encounter in our daily life, without having access to commercial 3D scanners? In this paper we present an automated system for generating geometric models of objects from two or more videos. Our system requires the specification of one known point in at least one frame of each video, which can be automatically determined using a fiducial marker such as a checkerboard or Augmented Reality (AR) marker. The remaining frames are automatically positioned in world space by using Structure-from-Motion techniques. By using multiple videos and merging results, a complete object mesh can be generated, without having to rely on hole filling. Code for our system is available from https://github.com/FlorisE/NeuralMeshing.
title NeuralMeshing: Complete Object Mesh Extraction from Casual Captures
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2508.16026