English

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

Computer Vision and Pattern Recognition 2024-08-22 v4 Robotics

Abstract

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.

Keywords

Cite

@article{arxiv.2207.08794,
  title  = {D$^3$FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance},
  author = {Xingyuan Yu and Weicai Ye and Xiyue Guo and Yuhang Ming and Jinyu Li and Hujun Bao and Zhaopeng Cui and Guofeng Zhang},
  journal= {arXiv preprint arXiv:2207.08794},
  year   = {2024}
}

Comments

Homepage: https://zju3dv.github.io/deflowslam

R2 v1 2026-06-25T01:01:28.937Z