SfM on-the-fly: Get better 3D from What You Capture

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhan, Zongqian, Yu, Yifei, Xia, Rui, Gan, Wentian, Xie, Hong, Perda, Giulio, Morelli, Luca, Remondino, Fabio, Wang, Xin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929419353849856
author Zhan, Zongqian
Yu, Yifei
Xia, Rui
Gan, Wentian
Xie, Hong
Perda, Giulio
Morelli, Luca
Remondino, Fabio
Wang, Xin
author_facet Zhan, Zongqian
Yu, Yifei
Xia, Rui
Gan, Wentian
Xie, Hong
Perda, Giulio
Morelli, Luca
Remondino, Fabio
Wang, Xin
contents In the last twenty years, Structure from Motion (SfM) has been a constant research hotspot in the fields of photogrammetry, computer vision, robotics etc., whereas real-time performance is just a recent topic of growing interest. This work builds upon the original on-the-fly SfM (Zhan et al., 2024) and presents an updated version with three new advancements to get better 3D from what you capture: (i) real-time image matching is further boosted by employing the Hierarchical Navigable Small World (HNSW) graphs, thus more true positive overlapping image candidates are faster identified; (ii) a self-adaptive weighting strategy is proposed for robust hierarchical local bundle adjustment to improve the SfM results; (iii) multiple agents are included for supporting collaborative SfM and seamlessly merge multiple 3D reconstructions into a complete 3D scene when commonly registered images appear. Various comprehensive experiments demonstrate that the proposed SfM method (named on-the-fly SfMv2) can generate more complete and robust 3D reconstructions in a high time-efficient way. Code is available at http://yifeiyu225.github.io/on-the-flySfMv2.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03939
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SfM on-the-fly: Get better 3D from What You Capture
Zhan, Zongqian
Yu, Yifei
Xia, Rui
Gan, Wentian
Xie, Hong
Perda, Giulio
Morelli, Luca
Remondino, Fabio
Wang, Xin
Computer Vision and Pattern Recognition
In the last twenty years, Structure from Motion (SfM) has been a constant research hotspot in the fields of photogrammetry, computer vision, robotics etc., whereas real-time performance is just a recent topic of growing interest. This work builds upon the original on-the-fly SfM (Zhan et al., 2024) and presents an updated version with three new advancements to get better 3D from what you capture: (i) real-time image matching is further boosted by employing the Hierarchical Navigable Small World (HNSW) graphs, thus more true positive overlapping image candidates are faster identified; (ii) a self-adaptive weighting strategy is proposed for robust hierarchical local bundle adjustment to improve the SfM results; (iii) multiple agents are included for supporting collaborative SfM and seamlessly merge multiple 3D reconstructions into a complete 3D scene when commonly registered images appear. Various comprehensive experiments demonstrate that the proposed SfM method (named on-the-fly SfMv2) can generate more complete and robust 3D reconstructions in a high time-efficient way. Code is available at http://yifeiyu225.github.io/on-the-flySfMv2.github.io/.
title SfM on-the-fly: Get better 3D from What You Capture
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.03939