ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera
This addresses the problem of real-time 3D reconstruction of moving objects for applications like robotics or VR, but it is incremental as it builds on prior fusion-based methods.
The paper tackled real-time dynamic scene reconstruction from a single depth camera, achieving robust and improved results for tangential and occluded motions by fusing geometry and using a segmentation-enhanced node graph with articulated motion priors.
This paper proposes a real-time dynamic scene reconstruction method capable of reproducing the motion, geometry, and segmentation simultaneously given live depth stream from a single RGB-D camera. Our approach fuses geometry frame by frame and uses a segmentation-enhanced node graph structure to drive the deformation of geometry in registration step. A two-level node motion optimization is proposed. The optimization space of node motions and the range of physically-plausible deformations are largely reduced by taking advantage of the articulated motion prior, which is solved by an efficient node graph segmentation method. Compared to previous fusion-based dynamic scene reconstruction methods, our experiments show robust and improved reconstruction results for tangential and occluded motions.