DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM
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_ | 1866929269620342784 |
|---|---|
| author | Li, Mingrui Zhou, Yiming Jiang, Guangan Deng, Tianchen Wang, Yangyang Wang, Hongyu |
| author_facet | Li, Mingrui Zhou, Yiming Jiang, Guangan Deng, Tianchen Wang, Yangyang Wang, Hongyu |
| contents | SLAM systems based on NeRF have demonstrated superior performance in rendering quality and scene reconstruction for static environments compared to traditional dense SLAM. However, they encounter tracking drift and mapping errors in real-world scenarios with dynamic interferences. To address these issues, we introduce DDN-SLAM, the first real-time dense dynamic neural implicit SLAM system integrating semantic features. To address dynamic tracking interferences, we propose a feature point segmentation method that combines semantic features with a mixed Gaussian distribution model. To avoid incorrect background removal, we propose a mapping strategy based on sparse point cloud sampling and background restoration. We propose a dynamic semantic loss to eliminate dynamic occlusions. Experimental results demonstrate that DDN-SLAM is capable of robustly tracking and producing high-quality reconstructions in dynamic environments, while appropriately preserving potential dynamic objects. Compared to existing neural implicit SLAM systems, the tracking results on dynamic datasets indicate an average 90% improvement in Average Trajectory Error (ATE) accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01545 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM Li, Mingrui Zhou, Yiming Jiang, Guangan Deng, Tianchen Wang, Yangyang Wang, Hongyu Computer Vision and Pattern Recognition Robotics SLAM systems based on NeRF have demonstrated superior performance in rendering quality and scene reconstruction for static environments compared to traditional dense SLAM. However, they encounter tracking drift and mapping errors in real-world scenarios with dynamic interferences. To address these issues, we introduce DDN-SLAM, the first real-time dense dynamic neural implicit SLAM system integrating semantic features. To address dynamic tracking interferences, we propose a feature point segmentation method that combines semantic features with a mixed Gaussian distribution model. To avoid incorrect background removal, we propose a mapping strategy based on sparse point cloud sampling and background restoration. We propose a dynamic semantic loss to eliminate dynamic occlusions. Experimental results demonstrate that DDN-SLAM is capable of robustly tracking and producing high-quality reconstructions in dynamic environments, while appropriately preserving potential dynamic objects. Compared to existing neural implicit SLAM systems, the tracking results on dynamic datasets indicate an average 90% improvement in Average Trajectory Error (ATE) accuracy. |
| title | DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2401.01545 |