Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Huan, Linxi"'
This paper proposes a shape anchor guided learning strategy (AncLearn) for robust holistic indoor scene understanding. We observe that the search space constructed by current methods for proposal feature grouping and instance point sampling often int
Externí odkaz:
http://arxiv.org/abs/2309.11133
The inference of topological principles is a key problem in structured reconstruction. We observe that wrongly predicted topological relationships are often incurred by the lack of holistic geometry clues in low-level features. Inspired by the fact t
Externí odkaz:
http://arxiv.org/abs/2309.09622
Publikováno v:
In Information Fusion January 2025 113
This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional n
Externí odkaz:
http://arxiv.org/abs/2011.09808
Semantic segmentation has been a hot topic across diverse research fields. Along with the success of deep convolutional neural networks, semantic segmentation has made great achievements and improvements, in terms of both urban scene parsing and indo
Externí odkaz:
http://arxiv.org/abs/1906.11428
Publikováno v:
In ISPRS Journal of Photogrammetry and Remote Sensing April 2022 186:301-314
Publikováno v:
In ISPRS Journal of Photogrammetry and Remote Sensing November 2021 181:99-112
Publikováno v:
In ISPRS Journal of Photogrammetry and Remote Sensing June 2021 176:42-53
Publikováno v:
In ISPRS Journal of Photogrammetry and Remote Sensing December 2020 170:15-28
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.