English

POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture

Computer Vision and Pattern Recognition 2021-03-30 v1

Abstract

We propose POse-guided SElective Fusion (POSEFusion), a single-view human volumetric capture method that leverages tracking-based methods and tracking-free inference to achieve high-fidelity and dynamic 3D reconstruction. By contributing a novel reconstruction framework which contains pose-guided keyframe selection and robust implicit surface fusion, our method fully utilizes the advantages of both tracking-based methods and tracking-free inference methods, and finally enables the high-fidelity reconstruction of dynamic surface details even in the invisible regions. We formulate the keyframe selection as a dynamic programming problem to guarantee the temporal continuity of the reconstructed sequence. Moreover, the novel robust implicit surface fusion involves an adaptive blending weight to preserve high-fidelity surface details and an automatic collision handling method to deal with the potential self-collisions. Overall, our method enables high-fidelity and dynamic capture in both visible and invisible regions from a single RGBD camera, and the results and experiments show that our method outperforms state-of-the-art methods.

Keywords

Cite

@article{arxiv.2103.15331,
  title  = {POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture},
  author = {Zhe Li and Tao Yu and Zerong Zheng and Kaiwen Guo and Yebin Liu},
  journal= {arXiv preprint arXiv:2103.15331},
  year   = {2021}
}

Comments

CVPR 2021 (Oral presentation), for more information, please refer to the projectpage http://www.liuyebin.com/posefusion/posefusion.html

R2 v1 2026-06-24T00:38:05.659Z