Dynamic Visual SLAM using a General 3D Prior
By: Xingguang Zhong , Liren Jin , Marija Popović and more
Potential Business Impact:
Helps robots see and map moving things.
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.
Similar Papers
Large-scale visual SLAM for in-the-wild videos
CV and Pattern Recognition
Makes robots understand new places from shaky videos.
The Dynamic Prior: Understanding 3D Structures for Casual Dynamic Videos
CV and Pattern Recognition
Helps cameras understand moving things in videos better.
Multi-Agent Monocular Dense SLAM With 3D Reconstruction Priors
Robotics
Robots build 3D maps faster with many cameras.