Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |