Towards Viewpoint Invariant 3D Human Pose Estimation


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.

DOI: 10.1007/978-3-319-46448-0_10

Extracted Key Phrases

16 Figures and Tables

Cite this paper

@inproceedings{Haque2016TowardsVI, 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}, booktitle={ECCV}, year={2016} }