Sparse Anchors for Visual Multi-Session Registration in Changing Environments
Sparse Anchors for Visual Multi-Session Registration in Changing Environments
This paper presents a method for registering new robotic trajectories to existing maps despite substantial environmental changes. The approach uses visual place recognition and feature matching to identify sparse, reliable absolute pose anchors, which are then combined with within-session relative constraints via robust pose-graph optimization.
The authors propose a method combining sparse absolute pose anchors with relative constraints to achieve robust multi-session registration in environments undergoing significant visual and structural changes, validated on the HILTI26 construction-site dataset.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported recall
94.4%
Reported trials
View original evidence
obust pose-graph optimization. We evaluate our approach on 15 cross-session experiments from the challenging HILTI26 construction-site dataset, covering substantial scene changes and difficult-to-match environments. Our method achieves 94.4% recall within 1m and 100.0% within 5m, outperforming independent image localization, which peaks at 65.3% and 70.7%, respectively, as well as direct registration of independently
Open source S5Reported recall
100%
Reported trials
View original evidence
obust pose-graph optimization. We evaluate our approach on 15 cross-session experiments from the challenging HILTI26 construction-site dataset, covering substantial scene changes and difficult-to-match environments. Our method achieves 94.4% recall within 1m and 100.0% within 5m, outperforming independent image localization, which peaks at 65.3% and 70.7%, respectively, as well as direct registration of independently
Open source S5
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
obust pose-graph optimization. We evaluate our approach on 15 cross-session experiments from the challenging HILTI26 construction-site dataset, covering substantial scene changes and difficult-to-match environments. Our method achieves 94.4% recall within 1m and 100.0% within 5m, outperforming independent image localization, which peaks at 65.3% and 70.7%, respectively, as well as direct registration of independently
Open source S5
reconstructed Structure-from-Motion geometry. Our results show that sparse, reliable absolute anchors can provide accurate and complete trajectory registration even when reliable cross-session correspondences are available only for part of the query session.
Open source S6
Sparse Anchors for Visual Multi-Session Registration in Changing Environments
Open source S1
arXiv:2611.05084v1 Announce Type: cross Abstract: Repeated robotic monitoring requires localization across visits to the same environment, even if the environment changes. Such changes can substantially reduce persistent visual content, and repetitive structures can lead to incorrect cross-session correspondences. In this paper, we address visual multi-session registration of a new data recording (the query session)
Open source S2
Source：arXiv Robotics — research abstracts · arxiv.org