Zobrazeno 1 - 10
of 120
pro vyhledávání: '"Zan Gojcic"'
Publikováno v:
Landslides, 18 (12)
We propose a novel fully automated deformation analysis pipeline capable of estimating real 3D displacement vectors from point cloud data. Different from the traditional methods that establish displacements based on the proximity in the Euclidean spa
Autor:
Robert Kenner, Valentin Gischig, Zan Gojcic, Yvain Quéau, Christian Kienholz, Daniel Figi, Reto Thöny, Yves Bonanomi
Publikováno v:
Landslides, 19 (6)
Lidar measurements and UAV photogrammetry provide high-resolution point clouds well suited for the investigation of slope deformations. Today, however, the information contained in these point clouds is rarely fully exploited. This study shows three
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::da5c3879a4d0c5988495b16766250ed4
https://hdl.handle.net/20.500.11850/540017
https://hdl.handle.net/20.500.11850/540017
Publikováno v:
Journal of Applied Geodesy, 15 (2)
The goal of classical geodetic data analysis is often to estimate distributional parameters like expected values and variances based on measurements that are subject to uncertainty due to unpredictable environmental effects and instrument specific no
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence.
We present SyNoRiM, a novel way to jointly register multiple non-rigid shapes by synchronizing the maps that relate learned functions defined on the point clouds. Even though the ability to process non-rigid shapes is critical in various applications
Publikováno v:
Journal of Applied Geodesy, 14 (2)
Areal deformation monitoring based on point clouds can be a very valuable alternative to the established point-based monitoring techniques, especially for deformation monitoring of natural scenes. However, established deformation analysis approaches
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198380
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5c50f6a69f97e9ded2e7d6aeffd70a9e
https://doi.org/10.1007/978-3-031-19839-7_39
https://doi.org/10.1007/978-3-031-19839-7_39
We present Neural Kernel Fields: a novel method for reconstructing implicit 3D shapes based on a learned kernel ridge regression. Our technique achieves state-of-the-art results when reconstructing 3D objects and large scenes from sparse oriented poi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15a453539862ebb1b1096229eeb3d9bc
http://arxiv.org/abs/2111.13674
http://arxiv.org/abs/2111.13674
Publikováno v:
CVPR
We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region. Different from previous work, our model is specifically designed to handle (also) point-cloud pairs with low overlap. Its key novelty is a
Publikováno v:
CVPR
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies. At the core of our method lies a deep architecture able to reason at the object
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff44971391c1cafabedfd812ce893b14
Publikováno v:
CVPR
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We present a novel, end-to-end learnable, multiview 3D point cloud registration algorithm. Registration of multiple scans typically follows a two-stage pipeline: the initial pairwise alignment and the globally consistent refinement. The former is oft