Abstract
We present an efficient subpixel refinement method using a learning-based approach called Linear Predictors. Two key ideas are shown in this paper. Firstly, we present a novel technique, called Symbolic Linear Predictors, which makes the learning step efficient for subpixel refinement. This makes our approach feasible for online applications without compromising accuracy, while taking advantage of the run-time efficiency of learning based approaches. Secondly, we show how Linear Predictors can be used to predict the expected alignment error, allowing us to use only the best keypoints in resource constrained applications. We show the efficiency and accuracy of our method through extensive experiments.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 |
| Publisher | IEEE, Institute of Electrical and Electronics Engineers |
| Pages | 8165-8173 |
| Number of pages | 9 |
| ISBN (Electronic) | 9781538664209 |
| DOIs | |
| Publication status | Published - 14 Dec 2018 |
| Event | IEEE Conference on Computer Vision and Pattern Recognition 2018 - Salt Lake City, United States of America Duration: 19 Jun 2018 → 21 Jun 2018 http://cvpr2018.thecvf.com/ |
Publication series
| Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|---|
| ISSN (Print) | 1063-6919 |
Conference
| Conference | IEEE Conference on Computer Vision and Pattern Recognition 2018 |
|---|---|
| Abbreviated title | CVPR 2018 |
| Country | United States of America |
| City | Salt Lake City |
| Period | 19/06/18 → 21/06/18 |
| Internet address |
Cite this
}
Efficient subpixel refinement with symbolic linear predictors. / Lui, Vincent; Geeves, Jonathon; Yii, Winston; Drummond, Tom.
Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 8165-8173 8578950 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other
TY - GEN
T1 - Efficient subpixel refinement with symbolic linear predictors
AU - Lui, Vincent
AU - Geeves, Jonathon
AU - Yii, Winston
AU - Drummond, Tom
PY - 2018/12/14
Y1 - 2018/12/14
N2 - We present an efficient subpixel refinement method using a learning-based approach called Linear Predictors. Two key ideas are shown in this paper. Firstly, we present a novel technique, called Symbolic Linear Predictors, which makes the learning step efficient for subpixel refinement. This makes our approach feasible for online applications without compromising accuracy, while taking advantage of the run-time efficiency of learning based approaches. Secondly, we show how Linear Predictors can be used to predict the expected alignment error, allowing us to use only the best keypoints in resource constrained applications. We show the efficiency and accuracy of our method through extensive experiments.
AB - We present an efficient subpixel refinement method using a learning-based approach called Linear Predictors. Two key ideas are shown in this paper. Firstly, we present a novel technique, called Symbolic Linear Predictors, which makes the learning step efficient for subpixel refinement. This makes our approach feasible for online applications without compromising accuracy, while taking advantage of the run-time efficiency of learning based approaches. Secondly, we show how Linear Predictors can be used to predict the expected alignment error, allowing us to use only the best keypoints in resource constrained applications. We show the efficiency and accuracy of our method through extensive experiments.
UR - http://www.scopus.com/inward/record.url?scp=85062854478&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00852
DO - 10.1109/CVPR.2018.00852
M3 - Conference Paper
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 8165
EP - 8173
BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PB - IEEE, Institute of Electrical and Electronics Engineers
ER -