Towards Viewpoint Invariant 3D Human Pose Estimation

23 Mar 2016  ·  Albert Haque, Boya Peng, Zelun Luo, Alexandre Alahi, Serena Yeung, Li Fei-Fei ·

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.

PDF Abstract

Datasets


Introduced in the Paper:

ITOP

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Pose Estimation ITOP front-view Multi-task learning + viewpoint invariance Mean mAP 77.4 # 6
Pose Estimation ITOP top-view Multi-task learning + viewpoint invariance Mean mAP 75.5 # 4

Methods


No methods listed for this paper. Add relevant methods here