A novel joint points and silhouette-based method to estimate 3D human pose and shape

TL;DR

This paper introduces a new method for estimating 3D human pose and shape from sparse-view images by combining joint points and silhouettes with a parametric model, achieving competitive results.

Contribution

The novel approach integrates joint points and silhouette correspondence with a parametric model, enabling effective 3D human pose and shape estimation from limited views.

Findings

Effective on synthetic and real data

Requires only sparse view images

Achieves competitive accuracy in pose and shape estimation

Abstract

This paper presents a novel method for 3D human pose and shape estimation from images with sparse views, using joint points and silhouettes, based on a parametric model. Firstly, the parametric model is fitted to the joint points estimated by deep learning-based human pose estimation. Then, we extract the correspondence between the parametric model of pose fitting and silhouettes on 2D and 3D space. A novel energy function based on the correspondence is built and minimized to fit parametric model to the silhouettes. Our approach uses sufficient shape information because the energy function of silhouettes is built from both 2D and 3D space. This also means that our method only needs images from sparse views, which balances data used and the required prior information. Results on synthetic data and real data demonstrate the competitive performance of our approach on pose and shape estimation of the human body.