000165592 001__ 165592
000165592 005__ 20260112132216.0
000165592 0247_ $$2doi$$a10.1109/LRA.2025.3617736
000165592 0248_ $$2sideral$$a147252
000165592 037__ $$aART-2025-147252
000165592 041__ $$aeng
000165592 100__ $$0(orcid)0000-0002-2555-374X$$aBerriel Martins, Tomás$$uUniversidad de Zaragoza
000165592 245__ $$aOpen-Vocabulary Online Semantic Mapping for SLAM
000165592 260__ $$c2025
000165592 5060_ $$aAccess copy available to the general public$$fUnrestricted
000165592 5203_ $$aThis letter presents an Open-Vocabulary Online 3D semantic mapping pipeline, that we denote by its acronym OVO. Given a sequence of posed RGB-D frames, we detect and track 3D segments, which we describe using CLIP vectors. These are computed from the viewpoints where they are observed by a novel CLIP merging method. Notably, our OVO has a significantly lower computational and memory footprint than offline baselines, while also showing better segmentation metrics than offline and online ones. Along with superior segmentation performance, we also show experimental results of our mapping contributions integrated with two different full SLAM backbones (Gaussian-SLAM and ORB-SLAM2), being the first ones using a neural network to merge CLIP descriptors and demonstrating end-to-end open-vocabulary online 3D mapping with loop closure.
000165592 536__ $$9info:eu-repo/grantAgreement/ES/AEI/PID2024-155886NB-I00$$9info:eu-repo/grantAgreement/ES/DGA/T45-23R$$9info:eu-repo/grantAgreement/ES/MICINN/PID2021-127685NB-I00
000165592 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es
000165592 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000165592 700__ $$aOswald, Martin R.
000165592 700__ $$0(orcid)0000-0003-1368-1151$$aCivera, Javier$$uUniversidad de Zaragoza
000165592 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000165592 773__ $$g10, 11 (2025), 11745-11752$$pIEEE Robot. autom. let.$$tIEEE Robotics and Automation Letters$$x2377-3766
000165592 8564_ $$s3106458$$uhttps://zaguan.unizar.es/record/165592/files/texto_completo.pdf$$yVersión publicada
000165592 8564_ $$s3310920$$uhttps://zaguan.unizar.es/record/165592/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000165592 909CO $$ooai:zaguan.unizar.es:165592$$particulos$$pdriver
000165592 951__ $$a2026-01-12-11:10:48
000165592 980__ $$aARTICLE