Object viewpoint estimation from 2D images is an essential task in computer vision. However, two issues hinder its progress: scarcity of training data with viewpoint annotations, and a lack of powerful features. Inspired by the growing availability of 3D models, we propose a framework to address both issues by combining render-based image synthesis and CNNs. We believe that 3D models have the potential in generating a large number of images of high variation, which can be well exploited by deep CNN with a high learning capacity. Towards this goal, we propose a scalable and overfit-resistant image synthesis pipeline, together with a novel CNN specifically tailored for the viewpoint estimation task. Experimentally, we show that the viewpoint estimation from our pipeline can significantly outperform state-of-the-art methods on PASCAL 3D+ benchmark.
@article{arxiv.1505.05641,
title = {Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views},
author = {Hao Su and Charles R. Qi and Yangyan Li and Leonidas Guibas},
journal= {arXiv preprint arXiv:1505.05641},
year = {2015}
}