Dynamic Visual SLAM using a General 3D Prior
This work addresses a key challenge in robotics, interactive visualization, and augmented reality by improving SLAM reliability in dynamic settings, though it appears incremental as it combines existing techniques.
The paper tackles the problem of robust camera pose estimation in dynamic natural environments by proposing a monocular visual SLAM system that integrates geometric patch-based online bundle adjustment with a feed-forward reconstruction model to filter dynamic regions and enhance depth prediction, achieving improved accuracy in dynamic scenes.
Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. However, this task is particularly challenging in dynamic natural environments, where scene dynamics can severely deteriorate camera pose estimation accuracy. In this work, we propose a novel monocular visual SLAM system that can robustly estimate camera poses in dynamic scenes. To this end, we leverage the complementary strengths of geometric patch-based online bundle adjustment and recent feed-forward reconstruction models. Specifically, we propose a feed-forward reconstruction model to precisely filter out dynamic regions, while also utilizing its depth prediction to enhance the robustness of the patch-based visual SLAM. By aligning depth prediction with estimated patches from bundle adjustment, we robustly handle the inherent scale ambiguities of the batch-wise application of the feed-forward reconstruction model.