Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Guillaume Bourmaud"'
Publikováno v:
Atmospheric Measurement Techniques
Atmospheric Measurement Techniques, 2022, 15 (15), pp.4411-4429. ⟨10.5194/amt-15-4411-2022⟩
Atmospheric Measurement Techniques, 2022, 15 (15), pp.4411-4429. ⟨10.5194/amt-15-4411-2022⟩
Spatiotemporal statistical learning has received increased attention in the past decade, due to spatially and temporally indexed data proliferation, especially collected from satellite remote sensing. In the mean time, observational studies of clouds
Publikováno v:
Conference on Computer Vision and Pattern Recognition
Conference on Computer Vision and Pattern Recognition, Jun 2021, Online, United States
CVPR
Conference on Computer Vision and Pattern Recognition, Jun 2021, Online, United States
CVPR
International audience; Absolute camera pose estimation is usually addressed by sequentially solving two distinct subproblems: First a feature matching problem that seeks to establish putative 2D-3D correspondences, and then a Perspective-n-Point pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc622c43032cb5787a5958b38812d946
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585792
ECCV (3)
ECCV (3)
Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under challenging con
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::165b9110614d762052fced8de55da73a
https://doi.org/10.1007/978-3-030-58580-8_37
https://doi.org/10.1007/978-3-030-58580-8_37
Publikováno v:
3DV
3DV, Sep 2019, Quebec, Canada
3DV, Sep 2019, Quebec, Canada
International audience; We propose a novel approach to feature point matching, suitable for robust and accurate outdoor visual localization in long-term scenarios. Given a query image, we first match it against a database of registered reference imag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78c158f3da4c06771e64d7e9f276314c
https://hal.archives-ouvertes.fr/hal-02353464
https://hal.archives-ouvertes.fr/hal-02353464
Publikováno v:
ICASSP
This paper addresses the problem of tracking a cluster of space debris sufficiently close to each other to be considered as a single ex-tended object. State-of-the-art random-matrix methods estimate the kinematics of the object centroid by assuming t
Autor:
Guillaume Bourmaud, Christopher Zach
Publikováno v:
ICCV
ICCV, Oct 2019, Seoul, South Korea
ICCV, Oct 2019, Seoul, South Korea
International audience; Robust cost optimization is the task of fitting parameters to data points containing outliers. In particular, we focus on large-scale computer vision problems, such as bundle adjustment , where Non-Linear Least Square (NLLS) s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f874ad79b7157d1570e9730e66dd2cab
https://hal.archives-ouvertes.fr/hal-02353424
https://hal.archives-ouvertes.fr/hal-02353424
Autor:
Guillaume Bourmaud, Christopher Zach
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012571
ECCV (12)
ECCV (12)
Robust cost optimization is the challenging task of fitting a large number of parameters to data points containing a significant and unknown fraction of outliers. In this work we identify three classes of deterministic second-order algorithms that ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::909dd17902742b4cc141c62f4240f408
https://doi.org/10.1007/978-3-030-01258-8_34
https://doi.org/10.1007/978-3-030-01258-8_34
Autor:
Guillaume Bourmaud, Christopher Zach
Publikováno v:
BMVC
Optimization of latent model parameters using robust formulations usually creates a large number of local minima due to the quasi-convex shape of the underlying robust kernel. Lifting the robust kernel, i.e. embedding the problem into a higher-dimens
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a55ae580974d6e25f7f21d936750e66b
https://hal.archives-ouvertes.fr/hal-01718012
https://hal.archives-ouvertes.fr/hal-01718012
Publikováno v:
Journal of Mathematical Imaging and Vision
Journal of Mathematical Imaging and Vision, Springer Verlag, 2015, 51 (1), ⟨10.1007/s10851-014-0517-0⟩
Journal of Mathematical Imaging and Vision, 2015, 51 (1), ⟨10.1007/s10851-014-0517-0⟩
Journal of Mathematical Imaging and Vision, Springer Verlag, 2015, 51 (1), ⟨10.1007/s10851-014-0517-0⟩
Journal of Mathematical Imaging and Vision, 2015, 51 (1), ⟨10.1007/s10851-014-0517-0⟩
International audience; In this paper we generalize the Continuous-Discrete Extended Kalman Filter (CD-EKF) to the case where the state and the observations evolve on connected unimodular matrix Lie groups. We propose a new assumed density filter cal
Autor:
Guillaume Bourmaud
Publikováno v:
Computer Vision – ECCV 2016 ISBN: 9783319464831
ECCV (8)
ECCV (8)
In this paper, we propose a novel algorithm dedicated to online motion averaging for large scale problems. To this end, we design a filter that continuously approximates the posterior distribution of the estimated transformations. In order to deal wi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9cbf8f533fb0404cdfc86be6fe2777b
https://hal.archives-ouvertes.fr/hal-01718015
https://hal.archives-ouvertes.fr/hal-01718015