Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation

TL;DR

This paper introduces SCOPE, a fast and efficient sparse constrained optimization method for 3D human pose and shape estimation, enabling real-time performance and outperforming existing optimization techniques.

Contribution

The paper presents a novel sparse constrained formulation and a real-time optimization algorithm for 3D human pose and shape estimation, significantly improving speed and scalability.

Findings

SCOPE achieves average convergence in 4 ms.

The method scales linearly with model complexity.

It outperforms existing optimization methods in benchmarks.

Abstract

We propose a novel sparse constrained formulation and from it derive a real-time optimization method for 3D human pose and shape estimation. Our optimization method, SCOPE (Sparse Constrained Optimization for 3D human Pose and shapE estimation), is orders of magnitude faster (avg. 4 ms convergence) than existing optimization methods, while being mathematically equivalent to their dense unconstrained formulation under mild assumptions. We achieve this by exploiting the underlying sparsity and constraints of our formulation to efficiently compute the Gauss-Newton direction. We show that this computation scales linearly with the number of joints and measurements of a complex 3D human model, in contrast to prior work where it scales cubically due to their dense unconstrained formulation. Based on our optimization method, we present a real-time motion capture framework that estimates 3D human poses and shapes from a single image at over 30 FPS. In benchmarks against state-of-the-art methods on multiple public datasets, our framework outperforms other optimization methods and achieves competitive accuracy against regression methods. Project page with code and videos: https://sites.google.com/view/scope-human/.