Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2509.13536 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914041422675968 |
|---|---|
| author | Bai, Yinlong Zhang, Hongxin Zhong, Sheng Niu, Junkai Li, Hai He, Yijia Zhou, Yi |
| author_facet | Bai, Yinlong Zhang, Hongxin Zhong, Sheng Niu, Junkai Li, Hai He, Yijia Zhou, Yi |
| contents | Recent advancements in 3D Gaussian Splatting (3DGS) have made a significant impact on rendering and reconstruction techniques. Current research predominantly focuses on improving rendering performance and reconstruction quality using high-performance desktop GPUs, largely overlooking applications for embedded platforms like micro air vehicles (MAVs). These devices, with their limited computational resources and memory, often face a trade-off between system performance and reconstruction quality. In this paper, we improve existing methods in terms of GPU memory usage while enhancing rendering quality. Specifically, to address redundant 3D Gaussian primitives in SLAM, we propose merging them in voxel space based on geometric similarity. This reduces GPU memory usage without impacting system runtime performance. Furthermore, rendering quality is improved by initializing 3D Gaussian primitives via Patch-Grid (PG) point sampling, enabling more accurate modeling of the entire scene. Quantitative and qualitative evaluations on publicly available datasets demonstrate the effectiveness of our improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13536 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MemGS: Memory-Efficient Gaussian Splatting for Real-Time SLAM Bai, Yinlong Zhang, Hongxin Zhong, Sheng Niu, Junkai Li, Hai He, Yijia Zhou, Yi Computer Vision and Pattern Recognition Recent advancements in 3D Gaussian Splatting (3DGS) have made a significant impact on rendering and reconstruction techniques. Current research predominantly focuses on improving rendering performance and reconstruction quality using high-performance desktop GPUs, largely overlooking applications for embedded platforms like micro air vehicles (MAVs). These devices, with their limited computational resources and memory, often face a trade-off between system performance and reconstruction quality. In this paper, we improve existing methods in terms of GPU memory usage while enhancing rendering quality. Specifically, to address redundant 3D Gaussian primitives in SLAM, we propose merging them in voxel space based on geometric similarity. This reduces GPU memory usage without impacting system runtime performance. Furthermore, rendering quality is improved by initializing 3D Gaussian primitives via Patch-Grid (PG) point sampling, enabling more accurate modeling of the entire scene. Quantitative and qualitative evaluations on publicly available datasets demonstrate the effectiveness of our improvements. |
| title | MemGS: Memory-Efficient Gaussian Splatting for Real-Time SLAM |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.13536 |