Enhancing Glass Surface Reconstruction via Depth Prior for Robot Navigation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zheng, Jiamin, Yu, Jingwen, Chen, Guangcheng, Zhang, Hong
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914533229985792
author Zheng, Jiamin
Yu, Jingwen
Chen, Guangcheng
Zhang, Hong
author_facet Zheng, Jiamin
Yu, Jingwen
Chen, Guangcheng
Zhang, Hong
contents Indoor robot navigation is often compromised by glass surfaces, which severely corrupt depth sensor measurements. While foundation models like Depth Anything 3 provide excellent geometric priors, they lack an absolute metric scale. We propose a training-free framework that leverages depth foundation models as a structural prior, employing a robust local RANSAC-based alignment to fuse it with raw sensor depth. This naturally avoids contamination from erroneous glass measurements and recovers an accurate metric scale. Furthermore, we introduce \ti{GlassRecon}, a novel RGB-D dataset with geometrically derived ground truth for glass regions. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art baselines, especially under severe sensor depth corruption. The dataset and related code will be released at https://github.com/jarvisyjw/GlassRecon.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18336
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Enhancing Glass Surface Reconstruction via Depth Prior for Robot Navigation
Zheng, Jiamin
Yu, Jingwen
Chen, Guangcheng
Zhang, Hong
Robotics
Computer Vision and Pattern Recognition
Indoor robot navigation is often compromised by glass surfaces, which severely corrupt depth sensor measurements. While foundation models like Depth Anything 3 provide excellent geometric priors, they lack an absolute metric scale. We propose a training-free framework that leverages depth foundation models as a structural prior, employing a robust local RANSAC-based alignment to fuse it with raw sensor depth. This naturally avoids contamination from erroneous glass measurements and recovers an accurate metric scale. Furthermore, we introduce \ti{GlassRecon}, a novel RGB-D dataset with geometrically derived ground truth for glass regions. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art baselines, especially under severe sensor depth corruption. The dataset and related code will be released at https://github.com/jarvisyjw/GlassRecon.
title Enhancing Glass Surface Reconstruction via Depth Prior for Robot Navigation
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.18336