Viewpoint Invariant 3D Human Pose Estimation with Recurrent Error Feedback
Authors:
Preprint
Abstract
We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve viewpoint invariance, our deep 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 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.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose EstimationInternational Journal of Computer Vision, 2016
- Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural NetworkInternational Journal of Computer Vision, 2014
- Robust Instance Recognition in Presence of Occlusion and Clutter2014
- Appearance Sharing for Collective Human Pose Estimation2013
- 2D Articulated Human Pose Estimation and Retrieval in (Almost) Unconstrained Still ImagesInternational Journal of Computer Vision, 2012
- Object Detection Using Strongly-Supervised Deformable Part Models2012
- Real-Time Human Pose Tracking from Range Data2012
- Viewpoint Invariant Texture Description Using Fractal AnalysisInternational Journal of Computer Vision, 2009
- Nonlinear Body Pose Estimation from Depth Images2005
- Estimating Human Body Configurations Using Shape Context Matching2002