Robust Estimation of 3D Human Poses from a Single Image

TL;DR

This paper introduces a robust method for estimating 3D human poses from single images by combining sparse basis representation, limb length constraints, and an $L_1$-norm loss to handle inaccuracies in 2D detections, outperforming existing methods.

Contribution

The authors propose a novel 3D pose estimation approach that integrates sparse basis modeling, limb constraints, and robust $L_1$-norm minimization, improving accuracy and robustness.

Findings

Outperforms state-of-the-art on three benchmark datasets.

Robust to inaccuracies in 2D joint detection.

Efficient optimization using alternating direction method.

Abstract

Human pose estimation is a key step to action recognition. We propose a method of estimating 3D human poses from a single image, which works in conjunction with an existing 2D pose/joint detector. 3D pose estimation is challenging because multiple 3D poses may correspond to the same 2D pose after projection due to the lack of depth information. Moreover, current 2D pose estimators are usually inaccurate which may cause errors in the 3D estimation. We address the challenges in three ways: (i) We represent a 3D pose as a linear combination of a sparse set of bases learned from 3D human skeletons. (ii) We enforce limb length constraints to eliminate anthropomorphically implausible skeletons. (iii) We estimate a 3D pose by minimizing the $L_1$-norm error between the projection of the 3D pose and the corresponding 2D detection. The $L_1$-norm loss term is robust to inaccurate 2D joint estimations. We use the alternating direction method (ADM) to solve the optimization problem efficiently. Our approach outperforms the state-of-the-arts on three benchmark datasets.