We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task learning problem, our model is able to selectively predict partial poses in the presence of noise and occlusion. Our approach leverages a convolutional and recurrent network architecture with a top-down error feedback mechanism to self-correct previous pose estimates in an end-to-end manner. We evaluate our model on a previously published depth dataset and a newly collected human pose dataset containing 100K annotated depth images from extreme viewpoints. Experiments show that our model achieves competitive performance on frontal views while achieving state-of-the-art performance on alternate viewpoints.
@article{arxiv.1603.07076,
title = {Towards Viewpoint Invariant 3D Human Pose Estimation},
author = {Albert Haque and Boya Peng and Zelun Luo and Alexandre Alahi and Serena Yeung and Li Fei-Fei},
journal= {arXiv preprint arXiv:1603.07076},
year = {2016}
}
Comments
European Conference on Computer Vision (ECCV) 2016