We present a robust, real-time RGB SLAM system that handles dynamic environments by leveraging differentiable Uncertainty-aware Bundle Adjustment. Traditional SLAM methods typically assume static scenes, leading to tracking failures in the presence of motion. Recent dynamic SLAM approaches attempt to address this challenge using predefined dynamic priors or uncertainty-aware mapping, but they remain limited when confronted with unknown dynamic objects or highly cluttered scenes where geometric mapping becomes unreliable. In contrast, our method estimates per-pixel uncertainty by exploiting multi-view visual feature inconsistency, enabling robust tracking and reconstruction even in real-world environments. The proposed system achieves state-of-the-art camera poses and scene geometry in cluttered dynamic scenarios while running in real time at around 10 FPS. Code and datasets are available at https://github.com/MoyangLi00/DROID-W.git.

翻译：我们提出了一种鲁棒的、实时的RGB SLAM系统，通过利用可微的不确定性感知束调整来处理动态环境。传统SLAM方法通常假设静态场景，在存在运动时会导致跟踪失败。最近的动态SLAM方法尝试使用预定义的动态先验或不确定性感知建图来解决这一挑战，但在面对未知动态物体或几何建图变得不可靠的高度杂乱场景时仍存在局限性。相比之下，我们的方法通过利用多视角视觉特征不一致性来估计每个像素的不确定性，即使在真实世界环境中也能实现鲁棒的跟踪和重建。所提出的系统在杂乱动态场景中实现了最先进的相机位姿和场景几何，同时以约10 FPS的实时速度运行。代码和数据集可在https://github.com/MoyangLi00/DROID-W.git获取。