3D Pose Regression Using Convolutional Neural Networks
Abstract
3D pose estimation is a key component of many important computer vision tasks such as autonomous navigation and 3D scene understanding. Most state-of-the-art approaches to 3D pose estimation solve this problem as a pose-classification problem in which the pose space is discretized into bins and a CNN classifier is used to predict a pose bin. We argue that the 3D pose space is continuous and propose to solve the pose estimation problem in a CNN regression framework with a suitable representation, data augmentation and loss function that captures the geometry of the pose space. Experiments on PASCAL3D+ show that the proposed 3D pose regression approach achieves competitive performance compared to the state-of-the-art.
Cite
Text
Mahendran et al. "3D Pose Regression Using Convolutional Neural Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.73Markdown
[Mahendran et al. "3D Pose Regression Using Convolutional Neural Networks." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/mahendran2017cvprw-3d/) doi:10.1109/CVPRW.2017.73BibTeX
@inproceedings{mahendran2017cvprw-3d,
title = {{3D Pose Regression Using Convolutional Neural Networks}},
author = {Mahendran, Siddharth and Ali, Haider and Vidal, René},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2017},
pages = {494-495},
doi = {10.1109/CVPRW.2017.73},
url = {https://mlanthology.org/cvprw/2017/mahendran2017cvprw-3d/}
}