EGS-SLAM: RGB-D Gaussian Splatting SLAM with Events
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916890112163840 |
|---|---|
| author | Chen, Siyu Yuan, Shenghai Nguyen, Thien-Minh Huang, Zhuyu Shi, Chenyang Jing, Jin Xie, Lihua |
| author_facet | Chen, Siyu Yuan, Shenghai Nguyen, Thien-Minh Huang, Zhuyu Shi, Chenyang Jing, Jin Xie, Lihua |
| contents | Gaussian Splatting SLAM (GS-SLAM) offers a notable improvement over traditional SLAM methods, enabling photorealistic 3D reconstruction that conventional approaches often struggle to achieve. However, existing GS-SLAM systems perform poorly under persistent and severe motion blur commonly encountered in real-world scenarios, leading to significantly degraded tracking accuracy and compromised 3D reconstruction quality. To address this limitation, we propose EGS-SLAM, a novel GS-SLAM framework that fuses event data with RGB-D inputs to simultaneously reduce motion blur in images and compensate for the sparse and discrete nature of event streams, enabling robust tracking and high-fidelity 3D Gaussian Splatting reconstruction. Specifically, our system explicitly models the camera's continuous trajectory during exposure, supporting event- and blur-aware tracking and mapping on a unified 3D Gaussian Splatting scene. Furthermore, we introduce a learnable camera response function to align the dynamic ranges of events and images, along with a no-event loss to suppress ringing artifacts during reconstruction. We validate our approach on a new dataset comprising synthetic and real-world sequences with significant motion blur. Extensive experimental results demonstrate that EGS-SLAM consistently outperforms existing GS-SLAM systems in both trajectory accuracy and photorealistic 3D Gaussian Splatting reconstruction. The source code will be available at https://github.com/Chensiyu00/EGS-SLAM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_07003 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EGS-SLAM: RGB-D Gaussian Splatting SLAM with Events Chen, Siyu Yuan, Shenghai Nguyen, Thien-Minh Huang, Zhuyu Shi, Chenyang Jing, Jin Xie, Lihua Robotics Gaussian Splatting SLAM (GS-SLAM) offers a notable improvement over traditional SLAM methods, enabling photorealistic 3D reconstruction that conventional approaches often struggle to achieve. However, existing GS-SLAM systems perform poorly under persistent and severe motion blur commonly encountered in real-world scenarios, leading to significantly degraded tracking accuracy and compromised 3D reconstruction quality. To address this limitation, we propose EGS-SLAM, a novel GS-SLAM framework that fuses event data with RGB-D inputs to simultaneously reduce motion blur in images and compensate for the sparse and discrete nature of event streams, enabling robust tracking and high-fidelity 3D Gaussian Splatting reconstruction. Specifically, our system explicitly models the camera's continuous trajectory during exposure, supporting event- and blur-aware tracking and mapping on a unified 3D Gaussian Splatting scene. Furthermore, we introduce a learnable camera response function to align the dynamic ranges of events and images, along with a no-event loss to suppress ringing artifacts during reconstruction. We validate our approach on a new dataset comprising synthetic and real-world sequences with significant motion blur. Extensive experimental results demonstrate that EGS-SLAM consistently outperforms existing GS-SLAM systems in both trajectory accuracy and photorealistic 3D Gaussian Splatting reconstruction. The source code will be available at https://github.com/Chensiyu00/EGS-SLAM. |
| title | EGS-SLAM: RGB-D Gaussian Splatting SLAM with Events |
| topic | Robotics |
| url | https://arxiv.org/abs/2508.07003 |