Probabilistic Dense Reconstruction from a Moving Camera
This work addresses the problem of real-time dense reconstruction for robotics and computer vision applications, presenting an incremental improvement over existing methods.
The paper tackles the challenge of online dense 3D reconstruction from a monocular moving camera by proposing a probabilistic method that uses spatial and temporal correlations to improve depth estimation robustness and accuracy, showing effectiveness through comparisons on TUM RGB-D SLAM and ICL-NUIM datasets.
This paper presents a probabilistic approach for online dense reconstruction using a single monocular camera moving through the environment. Compared to spatial stereo, depth estimation from motion stereo is challenging due to insufficient parallaxes, visual scale changes, pose errors, etc. We utilize both the spatial and temporal correlations of consecutive depth estimates to increase the robustness and accuracy of monocular depth estimation. An online, recursive, probabilistic scheme to compute depth estimates, with corresponding covariances and inlier probability expectations, is proposed in this work. We integrate the obtained depth hypotheses into dense 3D models in an uncertainty-aware way. We show the effectiveness and efficiency of our proposed approach by comparing it with state-of-the-art methods in the TUM RGB-D SLAM and ICL-NUIM dataset. Online indoor and outdoor experiments are also presented for performance demonstration.