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.
@article{arxiv.1708.05628,
title = {3D Pose Regression using Convolutional Neural Networks},
author = {Siddharth Mahendran and Haider Ali and Rene Vidal},
journal= {arXiv preprint arXiv:1708.05628},
year = {2017}
}