Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling

Abstract

We present a method for simultaneously estimating 3D human pose and body shape from a sparse set of wide-baseline camera views. We train a symmetric convolutional autoencoder with a dual loss that enforces learning of a latent representation that encodes skeletal joint positions, and at the same time learns a deep representation of volumetric body shape. We harness the latter to up-scale input volumetric data by a factor of $4\times$, whilst recovering a 3D estimate of joint positions with equal or greater accuracy than the state of the art. Inference runs in real-time (25 fps) and has the potential for passive human behaviour monitoring where there is a requirement for high fidelity estimation of human body shape and pose.

References in corpus (8)

• ADADELTA: An Adaptive Learning Rate Method
• Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
• Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
• Super-Resolution via Deep Learning
• Structured Prediction of 3D Human Pose with Deep Neural Networks
• Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation
• Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation
• Volumetric Super-Resolution of Multispectral Data