Multi-View Human Model Fitting Using Bone Orientation Constraint and Joints Triangulation Jordy Ajanohoun, Eric Paquette, Carlos Vázquez. Proceedings of the IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA, pages 1094-1098, 2021.

Abstract

We address 3D human pose and shape estimations from multi-view images. We use the SMPL body model, and regress the model parameters that best fit the shape and pose. To solve for the parameters, we first compute 3Djoint positions from 2D joint estimations on images by using a linear algebraic triangulation. Then, we fit the 3D parametric body model to the 3Djoints while imposing a bone orientation constraint between the 3D model and the corresponding body parts detected in the images. We do so by minimizing a new set of objective functions through a two-step optimization process that provides a good initialization for the refinement of the shape and pose parameters. Our approach is evaluated on the Human3.6M and HumanEva benchmarks, showing superior results with respect to state-of-the-art methods.

Keywords

Online version

Official published paper: https://doi.org/10.1109/ICIP42928.2021.9506718.

Pre-print version of the paper.

Additional material

Poster presentation.

BibTeX entry

@InProceedings{2021:Ajanohoun,
author = {Ajanohoun, Jordy and Paquette, Eric and Carlos V\'{a}zquez},
title = {Multi-View Human Model Fitting Using Bone Orientation Constraint and Joints Triangulation},
booktitle={Proceedings of the IEEE International Conference on Image Processing (ICIP)}, 
pages={1094-1098}
year = {2021},
}