MUTE-SLAM: Real-Time Neural SLAM with Multiple Tri-Plane Hash Representations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yan, Yifan, He, Ruomin, Liu, Zhenghua
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909321561899008
author Yan, Yifan
He, Ruomin
Liu, Zhenghua
author_facet Yan, Yifan
He, Ruomin
Liu, Zhenghua
contents We introduce MUTE-SLAM, a real-time neural RGB-D SLAM system employing multiple tri-plane hash-encodings for efficient scene representation. MUTE-SLAM effectively tracks camera positions and incrementally builds a scalable multi-map representation for both small and large indoor environments. As previous methods often require pre-defined scene boundaries, MUTE-SLAM dynamically allocates sub-maps for newly observed local regions, enabling constraint-free mapping without prior scene information. Unlike traditional grid-based methods, we use three orthogonal axis-aligned planes for hash-encoding scene properties, significantly reducing hash collisions and the number of trainable parameters. This hybrid approach not only ensures real-time performance but also enhances the fidelity of surface reconstruction. Furthermore, our optimization strategy concurrently optimizes all sub-maps intersecting with the current camera frustum, ensuring global consistency. Extensive testing on both real-world and synthetic datasets has shown that MUTE-SLAM delivers state-of-the-art surface reconstruction quality and competitive tracking performance across diverse indoor settings. The code is available at https://github.com/lumennYan/MUTE_SLAM.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17765
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MUTE-SLAM: Real-Time Neural SLAM with Multiple Tri-Plane Hash Representations
Yan, Yifan
He, Ruomin
Liu, Zhenghua
Computer Vision and Pattern Recognition
We introduce MUTE-SLAM, a real-time neural RGB-D SLAM system employing multiple tri-plane hash-encodings for efficient scene representation. MUTE-SLAM effectively tracks camera positions and incrementally builds a scalable multi-map representation for both small and large indoor environments. As previous methods often require pre-defined scene boundaries, MUTE-SLAM dynamically allocates sub-maps for newly observed local regions, enabling constraint-free mapping without prior scene information. Unlike traditional grid-based methods, we use three orthogonal axis-aligned planes for hash-encoding scene properties, significantly reducing hash collisions and the number of trainable parameters. This hybrid approach not only ensures real-time performance but also enhances the fidelity of surface reconstruction. Furthermore, our optimization strategy concurrently optimizes all sub-maps intersecting with the current camera frustum, ensuring global consistency. Extensive testing on both real-world and synthetic datasets has shown that MUTE-SLAM delivers state-of-the-art surface reconstruction quality and competitive tracking performance across diverse indoor settings. The code is available at https://github.com/lumennYan/MUTE_SLAM.
title MUTE-SLAM: Real-Time Neural SLAM with Multiple Tri-Plane Hash Representations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.17765