DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choe, Jaesung | ko |
dc.contributor.author | Joo, Kyungdon | ko |
dc.contributor.author | Rameau, Francois | ko |
dc.contributor.author | Kweon, In-So | ko |
dc.date.accessioned | 2023-09-07T03:00:30Z | - |
dc.date.available | 2023-09-07T03:00:30Z | - |
dc.date.created | 2023-09-07 | - |
dc.date.issued | 2021-05-30 | - |
dc.identifier.citation | 2021 IEEE International Conference on Robotics and Automation (ICRA), pp.12918 - 12924 | - |
dc.identifier.issn | 1050-4729 | - |
dc.identifier.uri | http://hdl.handle.net/10203/312302 | - |
dc.description.abstract | This paper presents a stereo object matching method that exploits both 2D contextual information from images as well as 3D object-level information. Unlike existing stereo matching methods that exclusively focus on the pixel-level correspondence between stereo images within a volumetric space (i.e., cost volume), we exploit this volumetric structure in a different manner. The cost volume explicitly encompasses 3D information along its disparity axis, therefore it is a privileged structure that can encapsulate the 3D contextual information from objects. However, it is not straightforward since the disparity values map the 31) metric space in a non-linear fashion. Thus, we present two novel strategies to handle 3D objectness in the cost volume space: selective sampling (RolSeled) and 2D-3D fusion (fusion-by-occupancy), which allow us to seamlessly incorporate 3D object-level information and achieve accurate depth performance near the object boundary regions. Our depth estimation achieves competitive performance in the KITTI dataset and the Virtual-KITTI 2.0 dataset. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Stereo Object Matching Network | - |
dc.type | Conference | - |
dc.identifier.wosid | 000771405404102 | - |
dc.identifier.scopusid | 2-s2.0-85104513987 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 12918 | - |
dc.citation.endingpage | 12924 | - |
dc.citation.publicationname | 2021 IEEE International Conference on Robotics and Automation (ICRA) | - |
dc.identifier.conferencecountry | CC | - |
dc.identifier.conferencelocation | Xi'an | - |
dc.identifier.doi | 10.1109/icra48506.2021.9562027 | - |
dc.contributor.localauthor | Kweon, In-So | - |
dc.contributor.nonIdAuthor | Joo, Kyungdon | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.