MGSO: Monocular Real-time Photometric SLAM with Efficient 3D Gaussian Splatting
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_ | 1866918191235596288 |
|---|---|
| author | Hu, Yan Song Abboud, Nicolas Ali, Muhammad Qasim Yang, Adam Srebrnjak Elhajj, Imad Asmar, Daniel Chen, Yuhao Zelek, John S. |
| author_facet | Hu, Yan Song Abboud, Nicolas Ali, Muhammad Qasim Yang, Adam Srebrnjak Elhajj, Imad Asmar, Daniel Chen, Yuhao Zelek, John S. |
| contents | Real-time SLAM with dense 3D mapping is computationally challenging, especially on resource-limited devices. The recent development of 3D Gaussian Splatting (3DGS) offers a promising approach for real-time dense 3D reconstruction. However, existing 3DGS-based SLAM systems struggle to balance hardware simplicity, speed, and map quality. Most systems excel in one or two of the aforementioned aspects but rarely achieve all. A key issue is the difficulty of initializing 3D Gaussians while concurrently conducting SLAM. To address these challenges, we present Monocular GSO (MGSO), a novel real-time SLAM system that integrates photometric SLAM with 3DGS. Photometric SLAM provides dense structured point clouds for 3DGS initialization, accelerating optimization and producing more efficient maps with fewer Gaussians. As a result, experiments show that our system generates reconstructions with a balance of quality, memory efficiency, and speed that outperforms the state-of-the-art. Furthermore, our system achieves all results using RGB inputs. We evaluate the Replica, TUM-RGBD, and EuRoC datasets against current live dense reconstruction systems. Not only do we surpass contemporary systems, but experiments also show that we maintain our performance on laptop hardware, making it a practical solution for robotics, A/R, and other real-time applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13055 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MGSO: Monocular Real-time Photometric SLAM with Efficient 3D Gaussian Splatting Hu, Yan Song Abboud, Nicolas Ali, Muhammad Qasim Yang, Adam Srebrnjak Elhajj, Imad Asmar, Daniel Chen, Yuhao Zelek, John S. Robotics Computer Vision and Pattern Recognition Real-time SLAM with dense 3D mapping is computationally challenging, especially on resource-limited devices. The recent development of 3D Gaussian Splatting (3DGS) offers a promising approach for real-time dense 3D reconstruction. However, existing 3DGS-based SLAM systems struggle to balance hardware simplicity, speed, and map quality. Most systems excel in one or two of the aforementioned aspects but rarely achieve all. A key issue is the difficulty of initializing 3D Gaussians while concurrently conducting SLAM. To address these challenges, we present Monocular GSO (MGSO), a novel real-time SLAM system that integrates photometric SLAM with 3DGS. Photometric SLAM provides dense structured point clouds for 3DGS initialization, accelerating optimization and producing more efficient maps with fewer Gaussians. As a result, experiments show that our system generates reconstructions with a balance of quality, memory efficiency, and speed that outperforms the state-of-the-art. Furthermore, our system achieves all results using RGB inputs. We evaluate the Replica, TUM-RGBD, and EuRoC datasets against current live dense reconstruction systems. Not only do we surpass contemporary systems, but experiments also show that we maintain our performance on laptop hardware, making it a practical solution for robotics, A/R, and other real-time applications. |
| title | MGSO: Monocular Real-time Photometric SLAM with Efficient 3D Gaussian Splatting |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.13055 |