English

ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera

Computer Vision and Pattern Recognition 2018-07-20 v1

Abstract

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.

Keywords

Cite

@article{arxiv.1807.07243,
  title  = {ArticulatedFusion: Real-time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera},
  author = {Chao Li and Zheheng Zhao and Xiaohu Guo},
  journal= {arXiv preprint arXiv:1807.07243},
  year   = {2018}
}

Comments

European Conference on Computer Vision 2018

R2 v1 2026-06-23T03:06:51.988Z