# Voxel Map for Visual SLAM

arXiv: https://arxiv.org/abs/2003.02247 · HTML: https://mlsanity.com/paper/2003.02247/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2020.

## Built on by (most cited first, 9 of 9)

- [PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environments](https://mlsanity.com/paper/2411.15800/) (2024)
- [RGB-Only Reconstruction of Tabletop Scenes for Collision-Free Manipulator Control](https://mlsanity.com/paper/2210.11668/) (2022)
- [ActiveInitSplat: How Active Image Selection Helps Gaussian Splatting](https://mlsanity.com/paper/2503.06859/) (2025)
- [DVN-SLAM: Dynamic Visual Neural SLAM Based on Local-Global Encoding](https://mlsanity.com/paper/2403.11776/) (2024)
- [GS-GVINS: A Tightly-integrated GNSS-Visual-Inertial Navigation System Augmented by 3D Gaussian Splatting](https://mlsanity.com/paper/2502.10975/) (2025)
- [GI-SLAM: Gaussian-Inertial SLAM](https://mlsanity.com/paper/2503.18275/) (2025)
- [A Collaborative Visual SLAM Framework for Service Robots](https://mlsanity.com/paper/2102.03228/) (2021)
- [A Comparison of Tiny-nerf versus Spatial Representations for 3d Reconstruction](https://mlsanity.com/paper/2301.11522/) (2023)
- [A Modular Vision-Language-Action Robotics Framework for Indoor Environments](https://mlsanity.com/paper/2606.31144/) (2026)

## Abstract (arXiv)

In modern visual SLAM systems, it is a standard practice to retrieve potential candidate map points from overlapping keyframes for further feature matching or direct tracking. In this work, we argue that keyframes are not the optimal choice for this task, due to several inherent limitations, such as weak geometric reasoning and poor scalability. We propose a voxel-map representation to efficiently retrieve map points for visual SLAM. In particular, we organize the map points in a regular voxel grid. Visible points from a camera pose are queried by sampling the camera frustum in a raycasting manner, which can be done in constant time using an efficient voxel hashing method. Compared with keyframes, the retrieved points using our method are geometrically guaranteed to fall in the camera field-of-view, and occluded points can be identified and removed to a certain extend. This method also naturally scales up to large scenes and complicated multicamera configurations. Experimental results show that our voxel map representation is as efficient as a keyframe map with 5 keyframes and provides significantly higher localization accuracy (average 46% improvement in RMSE) on the EuRoC dataset. The proposed voxel-map representation is a general approach to a fundamental functionality in visual SLAM and widely applicable.