MonoPerfCap
Authors:
Open Access
- 30 April 2018
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 37 (2) , 1-15
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 us 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.Keywords
Funding Information
- ERC Starting Grant project CapReal (335545)
This publication has 79 references indexed in Scilit:
- MovieReshapeACM Transactions on Graphics, 2010
- VideoMocapACM Transactions on Graphics, 2010
- Parametric reshaping of human bodies in imagesACM Transactions on Graphics, 2010
- Robust single-view geometry and motion reconstructionACM Transactions on Graphics, 2009
- Markerless garment captureACM Transactions on Graphics, 2008
- Performance capture from sparse multi-view videoACM Transactions on Graphics, 2008
- Articulated mesh animation from multi-view silhouettesACM Transactions on Graphics, 2008
- SCAPEACM Transactions on Graphics, 2005
- Estimating Articulated Human Motion with Covariance Scaled SamplingThe International Journal of Robotics Research, 2003
- Tracking and Modeling People in Video SequencesComputer Vision and Image Understanding, 2001