3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information

TL;DR

This paper introduces an end-to-end CNN approach for 3D human pose estimation that leverages 2D pose information and relative joint positions to improve accuracy, achieving competitive results on a standard dataset.

Contribution

The paper proposes a novel CNN-based method that incorporates 2D pose data and multiple joint relationships for enhanced 3D pose estimation.

Findings

Achieves comparable performance to state-of-the-art methods on Human 3.6m dataset.

Improving 3D pose accuracy by combining 2D pose info with multiple joint relative positions.

Demonstrates effectiveness of end-to-end CNN approach for 3D human pose estimation.

Abstract

While there has been a success in 2D human pose estimation with convolutional neural networks (CNNs), 3D human pose estimation has not been thoroughly studied. In this paper, we tackle the 3D human pose estimation task with end-to-end learning using CNNs. Relative 3D positions between one joint and the other joints are learned via CNNs. The proposed method improves the performance of CNN with two novel ideas. First, we added 2D pose information to estimate a 3D pose from an image by concatenating 2D pose estimation result with the features from an image. Second, we have found that more accurate 3D poses are obtained by combining information on relative positions with respect to multiple joints, instead of just one root joint. Experimental results show that the proposed method achieves comparable performance to the state-of-the-art methods on Human 3.6m dataset.