Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
Abstract: 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
Authors (4)
Mingyu Jeong
Eunsung Kim
Sehun Park
Andrew Jaeyong Choi
Submitted
October 28, 2025
Key Contributions
Presents NVSim, a framework for automatically constructing large-scale, navigable indoor simulators from image sequences, overcoming the limitations of traditional 3D scanning. It adapts 3D Gaussian Splatting for robotic traversal data and introduces floor-aware splatting and a mesh-free traversability algorithm.
Business Value
Significantly reduces the cost and effort required to create realistic simulation environments for training robots and AI agents, accelerating development cycles for applications in robotics, VR, and AR.