CVROJul 18, 2022

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

arXiv:2207.08794v415 citationsh-index: 71
Originality Highly original
AI Analysis

This addresses the challenge of accurate localization and mapping in dynamic environments for robotics and autonomous systems, representing a novel method for a known bottleneck.

The paper tackles the problem of robust SLAM in dynamic scenes by introducing a self-supervised method that decomposes motion into static and dynamic flows, achieving superior accuracy compared to other self-supervised methods and matching or surpassing some supervised methods.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes