Saved in:
Bibliographic Details
Main Authors: Jeong, Mingyu, Kim, Eunsung, Park, Sehun, Choi, Andrew Jaeyong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.24335
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909873841635328
author Jeong, Mingyu
Kim, Eunsung
Park, Sehun
Choi, Andrew Jaeyong
author_facet Jeong, Mingyu
Kim, Eunsung
Park, Sehun
Choi, Andrew Jaeyong
contents We present NVSim, a framework that automatically constructs large-scale, navigable indoor simulators from only common image sequences, overcoming the cost and scalability limitations of traditional 3D scanning. Our approach adapts 3D Gaussian Splatting to address visual artifacts on sparsely observed floors a common issue in robotic traversal data. We introduce Floor-Aware Gaussian Splatting to ensure a clean, navigable ground plane, and a novel mesh-free traversability checking algorithm that constructs a topological graph by directly analyzing rendered views. We demonstrate our system's ability to generate valid, large-scale navigation graphs from real-world data. A video demonstration is avilable at https://youtu.be/tTiIQt6nXC8
format Preprint
id arxiv_https___arxiv_org_abs_2510_24335
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NVSim: Novel View Synthesis Simulator for Large Scale Indoor Navigation
Jeong, Mingyu
Kim, Eunsung
Park, Sehun
Choi, Andrew Jaeyong
Robotics
Computer Vision and Pattern Recognition
We present NVSim, a framework that automatically constructs large-scale, navigable indoor simulators from only common image sequences, overcoming the cost and scalability limitations of traditional 3D scanning. Our approach adapts 3D Gaussian Splatting to address visual artifacts on sparsely observed floors a common issue in robotic traversal data. We introduce Floor-Aware Gaussian Splatting to ensure a clean, navigable ground plane, and a novel mesh-free traversability checking algorithm that constructs a topological graph by directly analyzing rendered views. We demonstrate our system's ability to generate valid, large-scale navigation graphs from real-world data. A video demonstration is avilable at https://youtu.be/tTiIQt6nXC8
title NVSim: Novel View Synthesis Simulator for Large Scale Indoor Navigation
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.24335