NVSim: Novel View Synthesis Simulator for Large Scale Indoor Navigation
This addresses the cost and scalability issues in indoor navigation for robotics, though it appears incremental as it builds on existing 3D Gaussian Splatting methods.
The paper tackles the problem of constructing large-scale, navigable indoor simulators from image sequences by introducing NVSim, which adapts 3D Gaussian Splatting to reduce visual artifacts and includes a mesh-free traversability algorithm, resulting in valid navigation graphs from real-world data.
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