3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)(2019)

Cited 1184|Views487
No score
Abstract
In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and effective semi-supervised training method that leverages unlabeled video data. We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints. In the supervised setting, our fully-convolutional model outperforms the previous best result from the literature by 6 mm mean per-joint position error on Human3.6M, corresponding to an error reduction of 11%, and the model also shows significant improvements on HumanEva-I. Moreover, experiments with back-projection show that it comfortably outperforms previous state-of-the-art results in semi-supervised settings where labeled data is scarce. Code and models are available at https://github.com/facebookresearch/VideoPose3D.
More
Translated text
Key words
Face,Gesture,and Body Pose
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined