Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization
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_ | 1866929325704478720 |
|---|---|
| author | Lipson, Lahav Deng, Jia |
| author_facet | Lipson, Lahav Deng, Jia |
| contents | We introduce a new system for Multi-Session SLAM, which tracks camera motion across multiple disjoint videos under a single global reference. Our approach couples the prediction of optical flow with solver layers to estimate camera pose. The backbone is trained end-to-end using a novel differentiable solver for wide-baseline two-view pose. The full system can connect disjoint sequences, perform visual odometry, and global optimization. Compared to existing approaches, our design is accurate and robust to catastrophic failures. Code is available at github.com/princeton-vl/MultiSlam_DiffPose |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15263 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization Lipson, Lahav Deng, Jia Computer Vision and Pattern Recognition We introduce a new system for Multi-Session SLAM, which tracks camera motion across multiple disjoint videos under a single global reference. Our approach couples the prediction of optical flow with solver layers to estimate camera pose. The backbone is trained end-to-end using a novel differentiable solver for wide-baseline two-view pose. The full system can connect disjoint sequences, perform visual odometry, and global optimization. Compared to existing approaches, our design is accurate and robust to catastrophic failures. Code is available at github.com/princeton-vl/MultiSlam_DiffPose |
| title | Multi-Session SLAM with Differentiable Wide-Baseline Pose Optimization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.15263 |