Recent advances in neural radiation fields (NeRF) and 3D Gaussian-based SLAM have achieved impressive localization accuracy and high-quality dense mapping in static scenes. However, these methods remain challenged in dynamic environments, where moving objects violate the static-world assumption and introduce inconsistent observations that degrade both camera tracking and map reconstruction. This motivates two fundamental problems: robustly identifying dynamic objects and modeling them online. To address these limitations, we propose CAD-SLAM, a Consistency-Aware Dynamic SLAM framework with dynamic-static decoupled mapping. Our key insight is that dynamic objects inherently violate cross-view and cross-time scene consistency. We detect object motion by analyzing geometric and texture discrepancies between historical map renderings and real-world observations. Once a moving object is identified, we perform bidirectional dynamic object tracking (both backward and forward in time) to achieve complete sequence-wise dynamic recognition. Our consistency-aware dynamic detection model achieves category-agnostic, instantaneous dynamic identification, which effectively mitigates motion-induced interference during localization and mapping. In addition, we introduce a dynamic-static decoupled mapping strategy that employs a temporal Gaussian model for online incremental dynamic modeling. Experiments conducted on multiple dynamic datasets demonstrate the flexible and accurate dynamic segmentation capabilities of our method, along with the state-of-the-art performance in both localization and mapping.

翻译：基于神经辐射场（NeRF）和3D高斯分布的SLAM技术的最新进展，在静态场景中已实现了令人印象深刻的定位精度和高质量的稠密建图。然而，这些方法在动态环境中仍然面临挑战，因为运动物体会违反静态世界的假设，并引入不一致的观测，从而降低相机跟踪和地图重建的质量。这引出了两个基本问题：如何鲁棒地识别动态物体以及如何在线建模它们。为了解决这些局限性，我们提出了CAD-SLAM，一个具有动静态解耦建图功能的一致性感知动态SLAM框架。我们的核心见解是，动态物体本质上违反了跨视角和跨时间的场景一致性。我们通过分析历史地图渲染结果与现实世界观测之间的几何和纹理差异来检测物体运动。一旦识别出运动物体，我们执行双向动态物体跟踪（在时间上向前和向后），以实现完整的序列级动态识别。我们的一致性感知动态检测模型实现了与类别无关的即时动态识别，有效减轻了定位和建图过程中由运动引起的干扰。此外，我们引入了一种动静态解耦的建图策略，该策略采用时序高斯模型进行在线增量式动态建模。在多个动态数据集上进行的实验表明，我们的方法具有灵活且准确的动态分割能力，同时在定位和建图方面均达到了最先进的性能。