MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images

Abstract

This paper proposes a statistical approach to 2D pose estimation from human images. The main problems with the standard supervised approach, which is based on a deep recognition (image-to-pose) model, are that it often yields anatomically implausible poses, and its performance is limited by the amount of paired data. To solve these problems, we propose a semi-supervised method that can make effective use of images with and without pose annotations. Specifically, we formulate a hierarchical generative model of poses and images by integrating a deep generative model of poses from pose features with that of images from poses and image features. We then introduce a deep recognition model that infers poses from images. Given images as observed data, these models can be trained jointly in a hierarchical variational autoencoding (image-to-pose-to-feature-to-pose-to-image) manner. The results of experiments show that the proposed reflective architecture makes estimated poses anatomically plausible, and the performance of pose estimation improved by integrating the recognition and generative models and also by feeding non-annotated images.

arXiv comment19 pages

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Auto-Encoding Variational Bayes
• DeepPose: Human Pose Estimation via Deep Neural Networks
• Semi-Supervised Learning with Deep Generative Models
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Human pose estimation via Convolutional Part Heatmap Regression
• Neural Variational Inference and Learning in Belief Networks