Absolute and Relative Pose Estimation in Refractive Multi View

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

Absolute and Relative Pose Estimation in Refractive Multi View. / Hu, Xiao; Lauze, Francois; Pedersen, Kim Steenstrup; Melou, Jean.

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). IEEE, 2021. s. 2569-2578.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Hu, X, Lauze, F, Pedersen, KS & Melou, J 2021, Absolute and Relative Pose Estimation in Refractive Multi View. i Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). IEEE, s. 2569-2578, 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 11/10/2021. https://doi.org/10.1109/ICCVW54120.2021.00290

APA

Hu, X., Lauze, F., Pedersen, K. S., & Melou, J. (2021). Absolute and Relative Pose Estimation in Refractive Multi View. I Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) (s. 2569-2578). IEEE. https://doi.org/10.1109/ICCVW54120.2021.00290

Vancouver

Hu X, Lauze F, Pedersen KS, Melou J. Absolute and Relative Pose Estimation in Refractive Multi View. I Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). IEEE. 2021. s. 2569-2578 https://doi.org/10.1109/ICCVW54120.2021.00290

Author

Hu, Xiao ; Lauze, Francois ; Pedersen, Kim Steenstrup ; Melou, Jean. / Absolute and Relative Pose Estimation in Refractive Multi View. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). IEEE, 2021. s. 2569-2578

Bibtex

@inproceedings{2cf66bac09374a958073d537510db417,
title = "Absolute and Relative Pose Estimation in Refractive Multi View",
abstract = "This paper investigates absolute and relative pose estimation under refraction, which are essential problems for refractive structure from motion. We first present an absolute pose estimation algorithm by leveraging an efficient iterative refinement. Then, we derive a novel refractive epipolar constraint for relative pose estimation. The epipolar constraint is established based on the virtual camera transformation, making it in a succinct form and can be efficiently optimized. Evaluations of the proposed algorithms on synthetic data show superior accuracy and computational efficiency to state-of-the-art methods. For further validation, we demonstrate the performance on real data and show the application in 3D reconstruction of objects under refraction.",
author = "Xiao Hu and Francois Lauze and Pedersen, {Kim Steenstrup} and Jean Melou",
year = "2021",
doi = "10.1109/ICCVW54120.2021.00290",
language = "English",
isbn = "978-1-6654-0191-3",
pages = "2569--2578",
booktitle = "Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)",
publisher = "IEEE",
note = "2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) ; Conference date: 11-10-2021 Through 17-10-2021",

}

RIS

TY - GEN

T1 - Absolute and Relative Pose Estimation in Refractive Multi View

AU - Hu, Xiao

AU - Lauze, Francois

AU - Pedersen, Kim Steenstrup

AU - Melou, Jean

PY - 2021

Y1 - 2021

N2 - This paper investigates absolute and relative pose estimation under refraction, which are essential problems for refractive structure from motion. We first present an absolute pose estimation algorithm by leveraging an efficient iterative refinement. Then, we derive a novel refractive epipolar constraint for relative pose estimation. The epipolar constraint is established based on the virtual camera transformation, making it in a succinct form and can be efficiently optimized. Evaluations of the proposed algorithms on synthetic data show superior accuracy and computational efficiency to state-of-the-art methods. For further validation, we demonstrate the performance on real data and show the application in 3D reconstruction of objects under refraction.

AB - This paper investigates absolute and relative pose estimation under refraction, which are essential problems for refractive structure from motion. We first present an absolute pose estimation algorithm by leveraging an efficient iterative refinement. Then, we derive a novel refractive epipolar constraint for relative pose estimation. The epipolar constraint is established based on the virtual camera transformation, making it in a succinct form and can be efficiently optimized. Evaluations of the proposed algorithms on synthetic data show superior accuracy and computational efficiency to state-of-the-art methods. For further validation, we demonstrate the performance on real data and show the application in 3D reconstruction of objects under refraction.

U2 - 10.1109/ICCVW54120.2021.00290

DO - 10.1109/ICCVW54120.2021.00290

M3 - Article in proceedings

SN - 978-1-6654-0191-3

SP - 2569

EP - 2578

BT - Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

PB - IEEE

T2 - 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

Y2 - 11 October 2021 through 17 October 2021

ER -

ID: 287177915