MonoPerfCap: Human Performance Capture from Monocular Video

ACM Transactions on Graphics (SIGGRAPH 2018, Vancouver, Canada)

Update: The dataset is now available for download


Download Video: HD (MP4, 169 MB)

Abstract

We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid surface deformations in general scenes. Human performance capture is a challenging problem due to the large range of articulation, potentially fast motion, and considerable non-rigid deformations, even from multi-view data. Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem. We tackle these challenges by a novel approach that employs sparse 2D and 3D human pose detections from a convolutional neural network using a batch-based pose estimation strategy. Joint recovery of per-batch motion allows to resolve the ambiguities of the monocular reconstruction problem based on a low dimensional trajectory subspace. In addition, we propose refinement of the surface geometry based on fully automatically extracted silhouettes to enable medium-scale non-rigid alignment. We demonstrate state-of-the-art performance capture results that enable exciting applications such as video editing and free viewpoint video, previously infeasible from monocular video. Our qualitative and quantitative evaluation demonstrates that our approach significantly outperforms previous monocular methods in terms of accuracy, robustness and scene complexity that can be handled.

Downloads


Citation

BibTeX, 1 KB

@article{Xu:2018:MHP:3191713.3181973,
 author = {Xu, Weipeng and Chatterjee, Avishek and Zollh\"{o}fer, Michael and Rhodin, Helge and Mehta, Dushyant and Seidel, Hans-Peter and Theobalt, Christian},
 title = {MonoPerfCap: Human Performance Capture From Monocular Video},
 journal = {ACM Trans. Graph.},
 issue_date = {June 2018},
 volume = {37},
 number = {2},
 month = may,
 year = {2018},
 issn = {0730-0301},
 pages = {27:1--27:15},
 articleno = {27},
 numpages = {15},
 url = {http://doi.acm.org/10.1145/3181973},
 doi = {10.1145/3181973},
 acmid = {3181973},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {3D pose estimation, Monocular performance capture, human body, non-rigid surface deformation},
} 
	  

Acknowledgments

This work is funded by the ERC Starting Grant project CapReal (335545).

Contact

For questions, clarifications, and access to the dataset, please get in touch with:
Weipeng Xu
wxu@mpi-inf.mpg.de