Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Benchmarking visual SLAM methods in mirror environments

Herbert, Peter, Wu, Jing ORCID:, Ji, Ze ORCID: and Lai, Yu-Kun ORCID: 2024. Benchmarking visual SLAM methods in mirror environments. Computational Visual Media 10 (2) , pp. 215-241. 10.1007/s41095-022-0329-x

[thumbnail of 41095_2022_Article_329.pdf]
PDF - Published Version
Available under License Creative Commons Attribution.

Download (10MB) | Preview


Visual simultaneous localisation and mapping (vSLAM) finds applications for indoor and outdoor navigation that routinely subjects it to visual complexities, particularly mirror reflections. The effect of mirror presence (time visible and its average size in the frame) was hypothesised to impact localisation and mapping performance, with systems using direct techniques expected to perform worse. Thus, a dataset, MirrEnv, of image sequences recorded in mirror environments, was collected, and used to evaluate the performance of existing representative methods. RGBD ORB-SLAM3 and BundleFusion appear to show moderate degradation of absolute trajectory error with increasing mirror duration, whilst the remaining results did not show significantly degraded localisation performance. The mesh maps generated proved to be very inaccurate, with real and virtual reflections colliding in the reconstructions. A discussion is given of the likely sources of error and robustness in mirror environments, outlining future directions for validating and improving vSLAM performance in the presence of planar mirrors. The MirrEnv dataset is available at

Item Type: Article
Date Type: Published Online
Status: Published
Schools: Advanced Research Computing @ Cardiff (ARCCA)
Computer Science & Informatics
Publisher: SpringerOpen
ISSN: 2096-0662
Funders: EPSRC
Date of First Compliant Deposit: 18 December 2023
Date of Acceptance: 18 December 2022
Last Modified: 11 Jun 2024 12:39

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics