论文标题
D $^3 $ FLOWLAM：自我监督的动态大满贯，流动运动分解和Dino指导
D$^3$FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance
论文作者
论文摘要
在本文中，我们介绍了一种自我监督的深猛击方法，该方法在动态场景中稳健地运行，同时准确地识别动态组件。我们的方法利用双流量表示进行静态流和动态流，从而促进了动态环境中有效的场景分解。我们基于此表示形式提出了一个动态更新模块，并开发了在动态方案中脱颖而出的密集大满贯系统。此外，我们还设计了一种使用Dino作为先验的自制训练计划，从而实现了无标签的培训。与其他自制方法相比，我们的方法达到了卓越的精度。在某些情况下，它还匹配甚至超过现有监督方法的性能。所有代码和数据将在接受后公开可用。
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.
