A Bayesian Framework for Sparse Representation-Based 3D Human Pose Estimation

TL;DR

This paper introduces a Bayesian approach to 3D human pose estimation from monocular images, leveraging shared sparse representations and probabilistic modeling to improve robustness with limited training data.

Contribution

It presents a novel Bayesian framework that jointly learns dictionaries and sparse codes, providing uncertainty estimates and enhanced reliability over existing methods.

Findings

Outperforms state-of-the-art pose estimation algorithms

Robust to small training datasets

Provides probabilistic estimates for pose and dictionary parameters

Abstract

A Bayesian framework for 3D human pose estimation from monocular images based on sparse representation (SR) is introduced. Our probabilistic approach aims at simultaneously learning two overcomplete dictionaries (one for the visual input space and the other for the pose space) with a shared sparse representation. Existing SR-based pose estimation approaches only offer a point estimation of the dictionary and the sparse codes. Therefore, they might be unreliable when the number of training examples is small. Our Bayesian framework estimates a posterior distribution for the sparse codes and the dictionaries from labeled training data. Hence, it is robust to overfitting on small-size training data. Experimental results on various human activities show that the proposed method is superior to the state of-the-art pose estimation algorithms.