Monocular Total Capture: Posing Face, Body, and Hands in the Wild

Abstract

We present the first method to capture the 3D total motion of a target person from a monocular view input. Given an image or a monocular video, our method reconstructs the motion from body, face, and fingers represented by a 3D deformable mesh model. We use an efficient representation called 3D Part Orientation Fields (POFs), to encode the 3D orientations of all body parts in the common 2D image space. POFs are predicted by a Fully Convolutional Network (FCN), along with the joint confidence maps. To train our network, we collect a new 3D human motion dataset capturing diverse total body motion of 40 subjects in a multiview system. We leverage a 3D deformable human model to reconstruct total body pose from the CNN outputs by exploiting the pose and shape prior in the model. We also present a texture-based tracking method to obtain temporally coherent motion capture output. We perform thorough quantitative evaluations including comparison with the existing body-specific and hand-specific methods, and performance analysis on camera viewpoint and human pose changes. Finally, we demonstrate the results of our total body motion capture on various challenging in-the-wild videos. Our code and newly collected human motion dataset will be publicly shared.

arXiv comment17 pages, 16 figures

References in corpus (18)

• DeepPose: Human Pose Estimation via Deep Neural Networks
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Embodied Hands: Modeling and Capturing Hands and Bodies Together
• Human pose estimation via Convolutional Part Heatmap Regression
• Stacked Hourglass Networks for Human Pose Estimation
• Capturing Hands in Action using Discriminative Salient Points and Physics Simulation
• Convolutional Pose Machines
• Fast and Robust Hand Tracking Using Detection-Guided Optimization
• MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild
• 3D Hand Pose Tracking and Estimation Using Stereo Matching
• A simple yet effective baseline for 3d human pose estimation
• Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
• OriNet: A Fully Convolutional Network for 3D Human Pose Estimation
• 3D Human Pose Estimation in the Wild by Adversarial Learning
• Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input
• It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data
• Panoptic Studio: A Massively Multiview System for Social Interaction Capture
• DRPose3D: Depth Ranking in 3D Human Pose Estimation

Cited by in corpus (11)

• MulayCap: Multi-layer Human Performance Capture Using A Monocular Video Camera
• DeepCap: Monocular Human Performance Capture Using Weak Supervision
• Single Image 3D Hand Reconstruction with Mesh Convolutions
• Delving Deep into Pixel Alignment Feature for Accurate Multi-view Human Mesh Recovery
• MonoClothCap: Towards Temporally Coherent Clothing Capture from Monocular RGB Video
• The Phong Surface: Efficient 3D Model Fitting using Lifted Optimization
• ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References
• Coherent Reconstruction of Multiple Humans from a Single Image
• Zoom in to the details of human-centric videos
• Exploring Pose Priors for Human Pose Estimation with Joint Angle Representations
• Efficient 2.5D Hand Pose Estimation via Auxiliary Multi-Task Training for Embedded Devices