DROID-SLAM
时间: 2023-09-13 07:09:49 浏览: 209
DROID-SLAM是一种用于视觉SLAM的端到端神经网络结构,它通过一个深度BA层来循环迭代地更新相机位姿和像素深度值。该系统在精度和鲁棒性方面比传统SLAM系统取得了更好的表现,并且在实验场景中几乎不会失败。尽管它只在单目视频上进行了训练,但在测试阶段,它仍然可以在双目和RGB-D视频上取得很好的性能。DROID-SLAM的开源代码可以在https://github.com/princeton-vl/DROID-SLAM找到。\[1\]\[2\]\[3\]
#### 引用[.reference_title]
- *1* [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras论文阅读笔记](https://blog.csdn.net/weixin_44120025/article/details/120280621)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^control_2,239^v3^insert_chatgpt"}} ] [.reference_item]
- *2* *3* [DROID-SLAM: 单目、双目、RGBD相机的深度视觉SLAM](https://blog.csdn.net/Yong_Qi2015/article/details/121298992)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^control_2,239^v3^insert_chatgpt"}} ] [.reference_item]
[ .reference_list ]
阅读全文