Saved in:
Bibliographic Details
Main Authors: Li, Runfa Blark, Shaghaghi, Mahdi, Suzuki, Keito, Liu, Xinshuang, Moparthi, Varun, Du, Bang, Curtis, Walker, Renschler, Martin, Lee, Ki Myung Brian, Atanasov, Nikolay, Nguyen, Truong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.11979
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915199801360384
author Li, Runfa Blark
Shaghaghi, Mahdi
Suzuki, Keito
Liu, Xinshuang
Moparthi, Varun
Du, Bang
Curtis, Walker
Renschler, Martin
Lee, Ki Myung Brian
Atanasov, Nikolay
Nguyen, Truong
author_facet Li, Runfa Blark
Shaghaghi, Mahdi
Suzuki, Keito
Liu, Xinshuang
Moparthi, Varun
Du, Bang
Curtis, Walker
Renschler, Martin
Lee, Ki Myung Brian
Atanasov, Nikolay
Nguyen, Truong
contents Simultaneous Localization and Mapping (SLAM) is one of the most important environment-perception and navigation algorithms for computer vision, robotics, and autonomous cars/drones. Hence, high quality and fast mapping becomes a fundamental problem. With the advent of 3D Gaussian Splatting (3DGS) as an explicit representation with excellent rendering quality and speed, state-of-the-art (SOTA) works introduce GS to SLAM. Compared to classical pointcloud-SLAM, GS-SLAM generates photometric information by learning from input camera views and synthesize unseen views with high-quality textures. However, these GS-SLAM fail when moving objects occupy the scene that violate the static assumption of bundle adjustment. The failed updates of moving GS affects the static GS and contaminates the full map over long frames. Although some efforts have been made by concurrent works to consider moving objects for GS-SLAM, they simply detect and remove the moving regions from GS rendering ("anti'' dynamic GS-SLAM), where only the static background could benefit from GS. To this end, we propose the first real-time GS-SLAM, "DynaGSLAM'', that achieves high-quality online GS rendering, tracking, motion predictions of moving objects in dynamic scenes while jointly estimating accurate ego motion. Our DynaGSLAM outperforms SOTA static & "Anti'' dynamic GS-SLAM on three dynamic real datasets, while keeping speed and memory efficiency in practice.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11979
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes
Li, Runfa Blark
Shaghaghi, Mahdi
Suzuki, Keito
Liu, Xinshuang
Moparthi, Varun
Du, Bang
Curtis, Walker
Renschler, Martin
Lee, Ki Myung Brian
Atanasov, Nikolay
Nguyen, Truong
Computer Vision and Pattern Recognition
Simultaneous Localization and Mapping (SLAM) is one of the most important environment-perception and navigation algorithms for computer vision, robotics, and autonomous cars/drones. Hence, high quality and fast mapping becomes a fundamental problem. With the advent of 3D Gaussian Splatting (3DGS) as an explicit representation with excellent rendering quality and speed, state-of-the-art (SOTA) works introduce GS to SLAM. Compared to classical pointcloud-SLAM, GS-SLAM generates photometric information by learning from input camera views and synthesize unseen views with high-quality textures. However, these GS-SLAM fail when moving objects occupy the scene that violate the static assumption of bundle adjustment. The failed updates of moving GS affects the static GS and contaminates the full map over long frames. Although some efforts have been made by concurrent works to consider moving objects for GS-SLAM, they simply detect and remove the moving regions from GS rendering ("anti'' dynamic GS-SLAM), where only the static background could benefit from GS. To this end, we propose the first real-time GS-SLAM, "DynaGSLAM'', that achieves high-quality online GS rendering, tracking, motion predictions of moving objects in dynamic scenes while jointly estimating accurate ego motion. Our DynaGSLAM outperforms SOTA static & "Anti'' dynamic GS-SLAM on three dynamic real datasets, while keeping speed and memory efficiency in practice.
title DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.11979