Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.15476 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917846358949888 |
|---|---|
| author | Wen, Long Li, Shixin Zhang, Yu Huang, Yuhong Lin, Jianjie Pan, Fengjunjie Bing, Zhenshan Knoll, Alois |
| author_facet | Wen, Long Li, Shixin Zhang, Yu Huang, Yuhong Lin, Jianjie Pan, Fengjunjie Bing, Zhenshan Knoll, Alois |
| contents | 3D Gaussian Splatting (3DGS) allows flexible adjustments to scene representation, enabling continuous optimization of scene quality during dense visual simultaneous localization and mapping (SLAM) in static environments. However, 3DGS faces challenges in handling environmental disturbances from dynamic objects with irregular movement, leading to degradation in both camera tracking accuracy and map reconstruction quality. To address this challenge, we develop an RGB-D dense SLAM which is called Gaussian Splatting SLAM in Dynamic Environments (Gassidy). This approach calculates Gaussians to generate rendering loss flows for each environmental component based on a designed photometric-geometric loss function. To distinguish and filter environmental disturbances, we iteratively analyze rendering loss flows to detect features characterized by changes in loss values between dynamic objects and static components. This process ensures a clean environment for accurate scene reconstruction. Compared to state-of-the-art SLAM methods, experimental results on open datasets show that Gassidy improves camera tracking precision by up to 97.9% and enhances map quality by up to 6%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15476 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Gassidy: Gaussian Splatting SLAM in Dynamic Environments Wen, Long Li, Shixin Zhang, Yu Huang, Yuhong Lin, Jianjie Pan, Fengjunjie Bing, Zhenshan Knoll, Alois Robotics 3D Gaussian Splatting (3DGS) allows flexible adjustments to scene representation, enabling continuous optimization of scene quality during dense visual simultaneous localization and mapping (SLAM) in static environments. However, 3DGS faces challenges in handling environmental disturbances from dynamic objects with irregular movement, leading to degradation in both camera tracking accuracy and map reconstruction quality. To address this challenge, we develop an RGB-D dense SLAM which is called Gaussian Splatting SLAM in Dynamic Environments (Gassidy). This approach calculates Gaussians to generate rendering loss flows for each environmental component based on a designed photometric-geometric loss function. To distinguish and filter environmental disturbances, we iteratively analyze rendering loss flows to detect features characterized by changes in loss values between dynamic objects and static components. This process ensures a clean environment for accurate scene reconstruction. Compared to state-of-the-art SLAM methods, experimental results on open datasets show that Gassidy improves camera tracking precision by up to 97.9% and enhances map quality by up to 6%. |
| title | Gassidy: Gaussian Splatting SLAM in Dynamic Environments |
| topic | Robotics |
| url | https://arxiv.org/abs/2411.15476 |