Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Yinlin, HU"'
Publikováno v:
Urban Mass Transit; 2024, Vol. 27 Issue 9, p249-259, 7p
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44:5472-5487
Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms. However, the derivatives of the eigenvectors tend to be numerically unstable, whether using the SVD to compute them analytically or using the Power Iteration
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f6d9a914d7fd2faf1db8169b1c4dfdb
https://doi.org/10.1109/tpami.2021.3072422
https://doi.org/10.1109/tpami.2021.3072422
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200854
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e39c535ea7d5882bceecd6f72c39dd6
https://doi.org/10.1007/978-3-031-20086-1_6
https://doi.org/10.1007/978-3-031-20086-1_6
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197680
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d9d01aed50e553b50ce5ba2f39c96b6
https://doi.org/10.1007/978-3-031-19769-7_7
https://doi.org/10.1007/978-3-031-19769-7_7
Publikováno v:
CVPR
6D pose estimation in space poses unique challenges that are not commonly encountered in the terrestrial setting. One of the most striking differences is the lack of atmospheric scattering, allowing objects to be visible from a great distance while c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08f5d93149b9cd4ee90172433038f669
Publikováno v:
CVPR
Most recent 6D pose estimation frameworks first rely on a deep network to establish correspondences between 3D object keypoints and 2D image locations and then use a variant of a RANSAC-based Perspective-n-Point (PnP) algorithm. This two-stage proces
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8534729e07c36a92dbe317316b9c5cb6
https://doi.org/10.1109/cvpr42600.2020.00300
https://doi.org/10.1109/cvpr42600.2020.00300
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 43(9)
Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector corresponding to th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::28cf3c095adb1f559f6abe0f9e583d62
https://pubmed.ncbi.nlm.nih.gov/32149625
https://pubmed.ncbi.nlm.nih.gov/32149625
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 28:2233-2245
Although the matching technique has been studied in various areas of computer vision for decades, efficient dense correspondence remains an open problem. In this paper, we present a simple but powerful matching method that works in a coarse-to-fine s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e13c47e882109b135add09a3f5e5f174
https://doi.org/10.1109/tcsvt.2017.2720175
https://doi.org/10.1109/tcsvt.2017.2720175
Publikováno v:
Image and Vision Computing. 70:1-10
Superpixel has become an essential processing unit in many computer vision systems, and superpixel segmentation of images is one of the most important step. In this paper, an efficient superpixel segmentation algorithm was proposed. We introduce a ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::161ff0da5e5442478cb2702d621411fe
https://doi.org/10.1016/j.imavis.2017.12.001
https://doi.org/10.1016/j.imavis.2017.12.001
Publikováno v:
CVPR
The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algori
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2f876c9ae4f8ca406d4f400439c40a7c
https://doi.org/10.1109/cvpr.2019.00350
https://doi.org/10.1109/cvpr.2019.00350