GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence

JiaWang Bian, Wen-Yan Lin, Yasuyuki Matsushita, Sai-Kit Yeung, Tan-Dat Nguyen, Ming-Ming Cheng

CVPR 2017

doi:10.1109/CVPR.2017.302 /cvpr/2017/bian2017cvpr-gms/

Abstract

Incorporating smoothness constraints into feature matching is known to enable ultra-robust matching. However, such formulations are both complex and slow, making them unsuitable for video applications. This paper proposes GMS (Grid-based Motion Statistics), a simple means of encapsulating motion smoothness as the statistical likelihood of a certain number of matches in a region. GMS enables translation of high match numbers into high match quality. This provides a real-time, ultra-robust correspondence system. Evaluation on videos, with low textures, blurs and wide-baselines show GMS consistently out-performs other real-time matchers and can achieve parity with more sophisticated, much slower techniques.

PDF CVPR Semantic Scholar

Cite

Text

Bian et al. "GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.302

Markdown

[Bian et al. "GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/bian2017cvpr-gms/) doi:10.1109/CVPR.2017.302

BibTeX

@inproceedings{bian2017cvpr-gms,
  title     = {{GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence}},
  author    = {Bian, JiaWang and Lin, Wen-Yan and Matsushita, Yasuyuki and Yeung, Sai-Kit and Nguyen, Tan-Dat and Cheng, Ming-Ming},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.302},
  url       = {https://mlanthology.org/cvpr/2017/bian2017cvpr-gms/}
}