OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913486663057408 |
|---|---|
| author | Wang, Meng Wang, Junyi Xia, Changqun Wang, Chen Qi, Yue |
| author_facet | Wang, Meng Wang, Junyi Xia, Changqun Wang, Chen Qi, Yue |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_17223 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping Wang, Meng Wang, Junyi Xia, Changqun Wang, Chen Qi, Yue Computer Vision and Pattern Recognition 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. |
| title | OG-Mapping: Octree-based Structured 3D Gaussians for Online Dense Mapping |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.17223 |