使用通用三维先验的动态视觉SLAM
Dynamic Visual SLAM using a General 3D Prior
把前馈重建模型的深度预测与 patch-based 在线 bundle adjustment 对齐，用其尺度消歧能力解决动态场景下单目 SLAM 的位姿漂移，可作为动态环境下 SLAM 前端过滤与深度先验融合的可复用范式。
原文依据 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
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论对相机姿态进行可靠的增量估计与三维重建，是实现机器人、交互式可视化与增强现实等多种应用的关键。然而，在动态自然环境中，在线SLAM尤为困难，因为场景动态会严重损害相机姿态估计的精度。在本工作中，我们提出了一种新颖的单目视觉SLAM系统，能够在动态场景中鲁棒地估计相机姿态。我们利用基于几何图块的在线光束法平差与近期前馈重建模型之间的互补优势。具体而言，我们提出一个前馈重建模型来精确滤除动态区域，同时利用其深度预测来增强基于图块的视觉SLAM的鲁棒性。通过将深度预测与光束法平差估计出的图块对齐，我们处理了前馈重建模型批量式应用所固有的尺度歧义。在多项任务上的大量实验表明，我们提出的方法相比最优方法具有更优的性能。
英文原文摘要 1121 字符
Reliable incremental estimation of camera poses and 3D reconstruction is key to enable various applications including robotics, interactive visualization, and augmented reality. However, online SLAM 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. 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 handle the inherent scale ambiguities of the batch-wise application of the feed-forward reconstruction model. Extensive experiments on multiple tasks show the superior performance of our proposed method compared to state-of-the-art approaches.