Quadtree-Accelerated Real-Time Monocular Dense Mapping

In this paper, we propose a novel mapping method for robotic navigation. High-quality dense depth maps are estimated and fused into 3D reconstructions in real-time using a single localized moving camera. The quadtree structure of the intensity image is used to reduce the computation burden by estimating the depth map in multiple resolutions. Both the quadtree-based pixel selection and the dynamic belief propagation are proposed to speed up the mapping process: pixels are selected and optimized with the computation resource according to their levels in the quadtree. Solved depth estimations are further interpolated and fused temporally into full resolution depth maps and fused into dense 3D maps using truncated signed distance function (TSDF). We compare our method with other state-of-the-art methods using the public datasets. Onboard UAV autonomous flight is also used to further prove the usability and efficiency of our method on portable devices. For the benefit of the community, the implementation is also released as open source at https://github.com/HKUST-Aerial-Robotics/open_quadtree_mapping.