D$^3$FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance

Autor:	Yu, Xingyuan, Ye, Weicai, Guo, Xiyue, Ming, Yuhang, Li, Jinyu, Bao, Hujun, Cui, Zhaopeng, Zhang, Guofeng
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Robotics
Druh dokumentu:	Working Paper
Popis:	In this paper, we introduce a self-supervised deep SLAM method that robustly operates in dynamic scenes while accurately identifying dynamic components. Our method leverages a dual-flow representation for static flow and dynamic flow, facilitating effective scene decomposition in dynamic environments. We propose a dynamic update module based on this representation and develop a dense SLAM system that excels in dynamic scenarios. In addition, we design a self-supervised training scheme using DINO as a prior, enabling label-free training. Our method achieves superior accuracy compared to other self-supervised methods. It also matches or even surpasses the performance of existing supervised methods in some cases. All code and data will be made publicly available upon acceptance. Comment: Homepage: https://zju3dv.github.io/deflowslam
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2207.08794 Zobrazit plný text záznamu View this record from Arxiv