Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Mingye Xu"'
Publikováno v:
Computational Visual Media, Vol 10, Iss 1, Pp 27-43 (2023)
Abstract Robustness and generalization are two challenging problems for learning point cloud representation. To tackle these problems, we first design a novel geometry coding model, which can effectively use an invariant eigengraph to group points wi
Externí odkaz:
https://doaj.org/article/0cdcc6200cfb44b695eaf1c95ec40535
Publikováno v:
IEEE Transactions on Industrial Informatics. :1-12
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf67d7c2b93fc583eab11be49a3a39bb
https://doi.org/10.1109/tii.2022.3215949
https://doi.org/10.1109/tii.2022.3215949
Point cloud completion aims to predict complete shape from its partial observation. Current approaches mainly consist of generation and refinement stages in a coarse-to-fine style. However, the generation stage often lacks robustness to tackle differ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7750d9971206c66d4d5f9bc8a29f1931
http://arxiv.org/abs/2207.05359
http://arxiv.org/abs/2207.05359
This paper investigates the indistinguishable points (difficult to predict label) in semantic segmentation for large-scale 3D point clouds. The indistinguishable points consist of those located in complex boundary, points with similar local textures
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eab17a43ee0ebf11a479f5d3934b1c64
Publikováno v:
AAAI
In spite of the recent progresses on classifying 3D point cloud with deep CNNs, large geometric transformations like rotation and translation remain challenging problem and harm the final classification performance. To address this challenge, we prop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::535dd099bc0f3ef39e0fc01c3b0dfcd2
http://arxiv.org/abs/1912.10644
http://arxiv.org/abs/1912.10644
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012366
ECCV (8)
ECCV (8)
Deep neural networks have enjoyed remarkable success for various vision tasks, however it remains challenging to apply CNNs to domains lacking a regular underlying structures such as 3D point clouds. Towards this we propose a novel convolutional arch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8cb6b01b60247b22a98e982ee5dc4afb
https://doi.org/10.1007/978-3-030-01237-3_6
https://doi.org/10.1007/978-3-030-01237-3_6
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.