A Coarse-to-Fine Model for 3D Pose Estimation and Sub-Category Recognition

Roozbeh Mottaghi, Yu Xiang, Silvio Savarese; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 418-426

Abstract


Despite the fact that object detection, 3D pose estimation, and sub-category recognition are highly correlated tasks, they are usually addressed independently from each other because of the huge space of parameters. To jointly model all of these tasks, we propose a coarse-to-fine hierarchical representation, where each level of the hierarchy represents objects at a different level of granularity. The hierarchical representation prevents performance loss, which is often caused by the increase in the number of parameters (as we consider more tasks to model), and the joint modeling enables resolving ambiguities that exist in independent modeling of these tasks. We augment PASCAL 3D+ dataset with annotations for these tasks and show that our hierarchical model is effective in joint modeling of object detection, 3D pose estimation, and sub-category recognition.

Related Material


[pdf]
[bibtex]
@InProceedings{Mottaghi_2015_CVPR,
author = {Mottaghi, Roozbeh and Xiang, Yu and Savarese, Silvio},
title = {A Coarse-to-Fine Model for 3D Pose Estimation and Sub-Category Recognition},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}