Papers › D³FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance

D³FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance

18 Jul 2022arXiv:2207.08794archive 2025-07-28

Xingyuan Yu, Weicai Ye, Xiyue Guo, Yuhang Ming, Jinyu Li, Hujun Bao, Zhaopeng Cui, Guofeng Zhang

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

zju3dv/DeFlowSLAM officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Pose EstimationSimultaneous Localization and Mapping

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DROID-SLAM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections