OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping
This work addresses storage and robustness issues in 3D reconstruction for applications like robotics or AR/VR, representing an incremental improvement over existing Gaussian-based methods.
The paper tackles the problem of redundancy and storage inefficiency in 3D Gaussian splatting for online dense mapping by introducing OG-Mapping, which uses octrees and structured 3D Gaussians to achieve more robust and realistic results with a compact model, requiring no post-processing.
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.