Articulated Pose Estimation with Tiny Synthetic Videos

June 2015

Articulated Pose Estimation with Tiny Synthetic Videos

Authors:

D. Park and D. Ramanan

Abstract:

We address the task of articulated pose estimation from video sequences. We consider an interactive setting where the initial pose is annotated in the first frame. Our system synthesizes a large number of hypothetical scenes with different poses and camera positions by applying geometric deformations to the first frame. We use these synthetic images to generate a custom labeled training set for the video in question. This training data is then used to learn a regressor (for future frames) that predicts joint locations from image data. Notably, our training set is so accurate that nearest-neighbor (NN) matching on low-resolution pixel features works well. As such, we name our underlying representation “tiny synthetic videos”. We present quantitative results the Friends benchmark dataset that suggests our simple approach matches or exceed state-of-the-art.
@workshop{Park-2015-121188,
author = {D. Park And D. Ramanan},
title = {Articulated Pose Estimation with Tiny Synthetic Videos},
booktitle = {Proceedings of CVPR '15 Workshops: CHA-LEARN Workshop on Looking at People},
year = {2015},
month = {June},
pages = {58 - 66},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.