ActiveGAMER: Active GAussian Mapping through Efficient Rendering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918135899095040 |
|---|---|
| author | Chen, Liyan Zhan, Huangying Chen, Kevin Xu, Xiangyu Yan, Qingan Cai, Changjiang Xu, Yi |
| author_facet | Chen, Liyan Zhan, Huangying Chen, Kevin Xu, Xiangyu Yan, Qingan Cai, Changjiang Xu, Yi |
| contents | We introduce ActiveGAMER, an active mapping system that utilizes 3D Gaussian Splatting (3DGS) to achieve high-quality, real-time scene mapping and exploration. Unlike traditional NeRF-based methods, which are computationally demanding and restrict active mapping performance, our approach leverages the efficient rendering capabilities of 3DGS, allowing effective and efficient exploration in complex environments. The core of our system is a rendering-based information gain module that dynamically identifies the most informative viewpoints for next-best-view planning, enhancing both geometric and photometric reconstruction accuracy. ActiveGAMER also integrates a carefully balanced framework, combining coarse-to-fine exploration, post-refinement, and a global-local keyframe selection strategy to maximize reconstruction completeness and fidelity. Our system autonomously explores and reconstructs environments with state-of-the-art geometric and photometric accuracy and completeness, significantly surpassing existing approaches in both aspects. Extensive evaluations on benchmark datasets such as Replica and MP3D highlight ActiveGAMER's effectiveness in active mapping tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_06897 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ActiveGAMER: Active GAussian Mapping through Efficient Rendering Chen, Liyan Zhan, Huangying Chen, Kevin Xu, Xiangyu Yan, Qingan Cai, Changjiang Xu, Yi Computer Vision and Pattern Recognition Robotics We introduce ActiveGAMER, an active mapping system that utilizes 3D Gaussian Splatting (3DGS) to achieve high-quality, real-time scene mapping and exploration. Unlike traditional NeRF-based methods, which are computationally demanding and restrict active mapping performance, our approach leverages the efficient rendering capabilities of 3DGS, allowing effective and efficient exploration in complex environments. The core of our system is a rendering-based information gain module that dynamically identifies the most informative viewpoints for next-best-view planning, enhancing both geometric and photometric reconstruction accuracy. ActiveGAMER also integrates a carefully balanced framework, combining coarse-to-fine exploration, post-refinement, and a global-local keyframe selection strategy to maximize reconstruction completeness and fidelity. Our system autonomously explores and reconstructs environments with state-of-the-art geometric and photometric accuracy and completeness, significantly surpassing existing approaches in both aspects. Extensive evaluations on benchmark datasets such as Replica and MP3D highlight ActiveGAMER's effectiveness in active mapping tasks. |
| title | ActiveGAMER: Active GAussian Mapping through Efficient Rendering |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2501.06897 |