MonoPerfCap: Human Performance Capture from Monocular Video

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.

arXiv commentAccepted to ACM TOG 2018, to be presented on SIGGRAPH 2018

References in corpus (12)

• DeepPose: Human Pose Estimation via Deep Neural Networks
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Stacked Hourglass Networks for Human Pose Estimation
• Towards Accurate Markerless Human Shape and Pose Estimation over Time
• Structured Prediction of 3D Human Pose with Deep Neural Networks
• Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation
• General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues
• Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
• Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
• General Dynamic Scene Reconstruction from Multiple View Video
• Model-based Outdoor Performance Capture
• Deep Kinematic Pose Regression

Cited by in corpus (3)

• Toward Immersive Communications in 6G
• Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network
• Learning to Estimate 3D Human Pose and Shape from a Single Color Image