Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation
Taosha Fan Kalyan Vasudev Alwala Donglai Xiang
Weipeng Xu Todd Murphey Mustafa Mukadam
Facebook AI Research Northwestern University Facebook Reality Lab Carnegie Mellon University
International Conference on Computer Vision (ICCV), 2021
Abstract
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.
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.
Results
Results
Computational Times
Computational Times
Qualitative Results
Qualitative Results
Videos
Videos
iccv_talk.mp4iccv_demo.mp4Bibtex
Bibtex
@article{fan2021revitalizing,
title={Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation},
author={Fan, Taosha and Alwala, Kalyan Vasudev and Xiang, Donglai and Xu, Weipeng and Murphey, Todd and Mukadam, Mustafa},
journal={Proceedings of the IEEE/CVF International Conference on Computer Vision},
year={2021}
}
Contact: taosha [dot] fan [at] u [dot] northwestern [dot] edu