Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.18284 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914773844623360 |
|---|---|
| author | Zhang, Zhiyao Zhang, Yunzhou Wu, Yanmin Zhao, Bin Wang, Xingshuo Tian, Rui |
| author_facet | Zhang, Zhiyao Zhang, Yunzhou Wu, Yanmin Zhao, Bin Wang, Xingshuo Tian, Rui |
| contents | With the emergence of Neural Radiance Fields (NeRF), neural implicit representations have gained widespread applications across various domains, including simultaneous localization and mapping. However, current neural implicit SLAM faces a challenging trade-off problem between performance and the number of parameters. To address this problem, we propose sparse tri-plane encoding, which efficiently achieves scene reconstruction at resolutions up to 512 using only 2~4% of the commonly used tri-plane parameters (reduced from 100MB to 2~4MB). On this basis, we design S3-SLAM to achieve rapid and high-quality tracking and mapping through sparsifying plane parameters and integrating orthogonal features of tri-plane. Furthermore, we develop hierarchical bundle adjustment to achieve globally consistent geometric structures and reconstruct high-resolution appearance. Experimental results demonstrate that our approach achieves competitive tracking and scene reconstruction with minimal parameters on three datasets. Source code will soon be available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_18284 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | S3-SLAM: Sparse Tri-plane Encoding for Neural Implicit SLAM Zhang, Zhiyao Zhang, Yunzhou Wu, Yanmin Zhao, Bin Wang, Xingshuo Tian, Rui Computer Vision and Pattern Recognition With the emergence of Neural Radiance Fields (NeRF), neural implicit representations have gained widespread applications across various domains, including simultaneous localization and mapping. However, current neural implicit SLAM faces a challenging trade-off problem between performance and the number of parameters. To address this problem, we propose sparse tri-plane encoding, which efficiently achieves scene reconstruction at resolutions up to 512 using only 2~4% of the commonly used tri-plane parameters (reduced from 100MB to 2~4MB). On this basis, we design S3-SLAM to achieve rapid and high-quality tracking and mapping through sparsifying plane parameters and integrating orthogonal features of tri-plane. Furthermore, we develop hierarchical bundle adjustment to achieve globally consistent geometric structures and reconstruct high-resolution appearance. Experimental results demonstrate that our approach achieves competitive tracking and scene reconstruction with minimal parameters on three datasets. Source code will soon be available. |
| title | S3-SLAM: Sparse Tri-plane Encoding for Neural Implicit SLAM |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.18284 |