Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera
arXiv:1803.05959
Abstract
We propose the first real-time approach for the egocentric estimation of 3D human body pose in a wide range of unconstrained everyday activities. This setting has a unique set of challenges, such as mobility of the hardware setup, and robustness to long capture sessions with fast recovery from tracking failures. We tackle these challenges based on a novel lightweight setup that converts a standard baseball cap to a device for high-quality pose estimation based on a single cap-mounted fisheye camera. From the captured egocentric live stream, our CNN based 3D pose estimation approach runs at 60Hz on a consumer-level GPU. In addition to the novel hardware setup, our other main contributions are: 1) a large ground truth training corpus of top-down fisheye images and 2) a novel disentangled 3D pose estimation approach that takes the unique properties of the egocentric viewpoint into account. As shown by our evaluation, we achieve lower 3D joint error as well as better 2D overlay than the existing baselines.
arXiv commentIEEE TVCG Proc. VR 2019. Webpage: http://gvv.mpi-inf.mpg.de/projects/wxu/Mo2Cap2/
References in corpus (12)
- ADADELTA: An Adaptive Learning Rate Method
- VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- Learning from Synthetic Humans
- Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
- Fast and Robust Hand Tracking Using Detection-Guided Optimization
- MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
- Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
- Synthesizing Training Images for Boosting Human 3D Pose Estimation
- 3D Hand Pose Detection in Egocentric RGB-D Images
- Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs
- Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video
- Model-based Outdoor Performance Capture