# GS-PRM: Gaussian Visual Roadmap for Image-Goal Navigation

arXiv: https://arxiv.org/abs/2610.19541 · HTML: https://mlsanity.com/paper/2610.19541/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in SLAM and driving scene reconstruction, one of 15 directions in 3D reconstruction and neural rendering.
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Placed in

- 3D reconstruction and neural rendering / [SLAM and driving scene reconstruction](https://mlsanity.com/recon3d/slam-and-driving-scene-reconstruction/)

## Builds on (most cited first, 19 of 19)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)
- [Splat-Nav: Safe Real-Time Robot Navigation in Gaussian Splatting Maps](https://mlsanity.com/paper/2403.02751/) (2024)
- [PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning](https://mlsanity.com/paper/1710.03937/) (2017)
- [Memory-Augmented Reinforcement Learning for Image-Goal Navigation](https://mlsanity.com/paper/2101.05181/) (2021)
- [GaussNav: Gaussian Splatting for Visual Navigation](https://mlsanity.com/paper/2403.11625/) (2024)
- [Renderable Neural Radiance Map for Visual Navigation](https://mlsanity.com/paper/2303.00304/) (2023)
- [iPlanner: Imperative Path Planning](https://mlsanity.com/paper/2302.11434/) (2023)
- [GHIL-Glue: Hierarchical Control with Filtered Subgoal Images](https://mlsanity.com/paper/2410.20018/) (2024)
- [GSplatVNM: Point-of-View Synthesis for Visual Navigation Models Using Gaussian Splatting](https://mlsanity.com/paper/2503.05152/) (2025)
- [GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting](https://mlsanity.com/paper/2412.20056/) (2024)
- [3DGSNav: Enhancing Vision-Language Model Reasoning for Object Navigation via Active 3D Gaussian Splatting](https://mlsanity.com/paper/2602.12159/) (2026)
- [Splatblox: Traversability-Aware Gaussian Splatting for Outdoor Robot Navigation](https://mlsanity.com/paper/2511.18525/) (2025)
- [DevGRU: Depth-guided Visual Navigation using a Collision-aware Recurrent Model](https://mlsanity.com/paper/2608.18470/) (2026)

## Abstract (arXiv)

Image-goal navigation requires a global planner that connects visually specified endpoints while providing observations that a local policy can follow. Three-dimensional Gaussian Splatting (3DGS) provides map-registered RGB, opacity, and depth renderings, but does not explicitly encode navigable topology. We introduce GS-PRM, a Gaussian visual roadmap whose milestones, local connections, and visual references are constructed directly through 3DGS rendering without deriving an occupancy grid or signed distance field. We define render-based collision-free (RC-free) configurations and paths. Panoramic depth supplies conservative clearance for milestone validation and adaptive coverage, while edge-aligned orthographic rendering tests the robot's swept volume. We establish conditional soundness and sufficient conditions for deterministic query completeness and probabilistic construction completeness of GS-PRM. To validate the performance of GS-PRM, we conduct experiments in both simulated and real-world environments, demonstrating long-horizon navigation using goal-conditioned policies guided by GS-PRM. Compared with a state-of-the-art 3DGS-based navigation system, our GS-PRM-based navigation system achieves up to a twice higher average success rate and reduces travel time by up to 57.2% when both systems complete the navigation task.