Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition

Qiang Hao, Rui Cai, Zhiwei Li, Lei Zhang, Yanwei Pang, Feng Wu, Yong Rui; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 899-906

Abstract


3D model-based object recognition has been a noticeable research trend in recent years. Common methods find 2D-to-3D correspondences and make recognition decisions by pose estimation, whose efficiency usually suffers from noisy correspondences caused by the increasing number of target objects. To overcome this scalability bottleneck, we propose an efficient 2D-to-3D correspondence filtering approach, which combines a light-weight neighborhoodbased step with a finer-grained pairwise step to remove spurious correspondences based on 2D/3D geometric cues. On a dataset of 300 3D objects, our solution achieves ~10 times speed improvement over the baseline, with a comparable recognition accuracy. A parallel implementation on a quad-core CPU can run at ~3fps for 1280x720 images.

Related Material


[pdf]
[bibtex]
@InProceedings{Hao_2013_CVPR,
author = {Hao, Qiang and Cai, Rui and Li, Zhiwei and Zhang, Lei and Pang, Yanwei and Wu, Feng and Rui, Yong},
title = {Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}