OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping

TL;DR

OG-Mapping introduces an efficient, robust online dense mapping method using octree-structured 3D Gaussians, improving scene detail recovery and reducing storage and noise sensitivity issues in RGB-D mapping.

Contribution

It combines sparse octrees with structured 3D Gaussians and employs a dynamic keyframe window for enhanced robustness and efficiency in scene mapping.

Findings

Outperforms existing Gaussian-based methods in realism and robustness.

Achieves compact model size without additional post-processing.

Effectively handles false local minima and scene detail recovery.

Abstract

3D Gaussian splatting (3DGS) has recently demonstrated promising advancements in RGB-D online dense mapping. Nevertheless, existing methods excessively rely on per-pixel depth cues to perform map densification, which leads to significant redundancy and increased sensitivity to depth noise. Additionally, explicitly storing 3D Gaussian parameters of room-scale scene poses a significant storage challenge. In this paper, we introduce OG-Mapping, which leverages the robust scene structural representation capability of sparse octrees, combined with structured 3D Gaussian representations, to achieve efficient and robust online dense mapping. Moreover, OG-Mapping employs an anchor-based progressive map refinement strategy to recover the scene structures at multiple levels of detail. Instead of maintaining a small number of active keyframes with a fixed keyframe window as previous approaches do, a dynamic keyframe window is employed to allow OG-Mapping to better tackle false local minima and forgetting issues. Experimental results demonstrate that OG-Mapping delivers more robust and superior realism mapping results than existing Gaussian-based RGB-D online mapping methods with a compact model, and no additional post-processing is required.