Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202459445> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3202459445 abstract "Category-level 6D object pose estimation aims to predict the position and orientation for unseen objects, which plays a pillar role in many scenarios such as robotics and augmented reality. The significant intra-class variation is the bottleneck challenge in this task yet remains unsolved so far. In this paper, we take advantage of category prior to overcome this problem by innovating a structure-guided prior adaptation scheme to accurately estimate 6D pose for individual objects. Different from existing prior based methods, given one object and its corresponding category prior, we propose to leverage their structure similarity to dynamically adapt the prior to the observed object. The prior adaptation intrinsically associates the adopted prior with different objects, from which we can accurately reconstruct the 3D canonical model of the specific object for pose estimation. To further enhance the structure characteristic of objects, we extract low-rank structure points from the dense object point cloud, therefore more efficiently incorporating sparse structural information during prior adaptation. Extensive experiments on CAMERA25 and REAL275 benchmarks demonstrate significant performance improvement. Project homepage: https://www.cse.cuhk.edu.hk/˜kaichen/projects/sgpa/sgpa.html." @default.
- W3202459445 created "2021-10-11" @default.
- W3202459445 creator A5074339191 @default.
- W3202459445 creator A5090516040 @default.
- W3202459445 date "2021-10-01" @default.
- W3202459445 modified "2023-10-05" @default.
- W3202459445 title "SGPA: Structure-Guided Prior Adaptation for Category-Level 6D Object Pose Estimation" @default.
- W3202459445 cites W2128019145 @default.
- W3202459445 cites W2194775991 @default.
- W3202459445 cites W2472269674 @default.
- W3202459445 cites W2560023338 @default.
- W3202459445 cites W2921849174 @default.
- W3202459445 cites W2963177347 @default.
- W3202459445 cites W2963756608 @default.
- W3202459445 cites W2963892972 @default.
- W3202459445 cites W2964249569 @default.
- W3202459445 cites W2998787775 @default.
- W3202459445 cites W3010276570 @default.
- W3202459445 cites W3034572187 @default.
- W3202459445 cites W3034597466 @default.
- W3202459445 cites W3034712732 @default.
- W3202459445 cites W3034986117 @default.
- W3202459445 cites W3035131925 @default.
- W3202459445 cites W3035424742 @default.
- W3202459445 cites W3090584485 @default.
- W3202459445 cites W3091357794 @default.
- W3202459445 cites W3193686508 @default.
- W3202459445 doi "https://doi.org/10.1109/iccv48922.2021.00277" @default.
- W3202459445 hasPublicationYear "2021" @default.
- W3202459445 type Work @default.
- W3202459445 sameAs 3202459445 @default.
- W3202459445 citedByCount "31" @default.
- W3202459445 countsByYear W32024594452022 @default.
- W3202459445 countsByYear W32024594452023 @default.
- W3202459445 crossrefType "proceedings-article" @default.
- W3202459445 hasAuthorship W3202459445A5074339191 @default.
- W3202459445 hasAuthorship W3202459445A5090516040 @default.
- W3202459445 hasConcept C103278499 @default.
- W3202459445 hasConcept C115961682 @default.
- W3202459445 hasConcept C119857082 @default.
- W3202459445 hasConcept C120665830 @default.
- W3202459445 hasConcept C121332964 @default.
- W3202459445 hasConcept C131979681 @default.
- W3202459445 hasConcept C139807058 @default.
- W3202459445 hasConcept C153083717 @default.
- W3202459445 hasConcept C153180895 @default.
- W3202459445 hasConcept C154945302 @default.
- W3202459445 hasConcept C2781238097 @default.
- W3202459445 hasConcept C31972630 @default.
- W3202459445 hasConcept C36613465 @default.
- W3202459445 hasConcept C41008148 @default.
- W3202459445 hasConcept C52102323 @default.
- W3202459445 hasConceptScore W3202459445C103278499 @default.
- W3202459445 hasConceptScore W3202459445C115961682 @default.
- W3202459445 hasConceptScore W3202459445C119857082 @default.
- W3202459445 hasConceptScore W3202459445C120665830 @default.
- W3202459445 hasConceptScore W3202459445C121332964 @default.
- W3202459445 hasConceptScore W3202459445C131979681 @default.
- W3202459445 hasConceptScore W3202459445C139807058 @default.
- W3202459445 hasConceptScore W3202459445C153083717 @default.
- W3202459445 hasConceptScore W3202459445C153180895 @default.
- W3202459445 hasConceptScore W3202459445C154945302 @default.
- W3202459445 hasConceptScore W3202459445C2781238097 @default.
- W3202459445 hasConceptScore W3202459445C31972630 @default.
- W3202459445 hasConceptScore W3202459445C36613465 @default.
- W3202459445 hasConceptScore W3202459445C41008148 @default.
- W3202459445 hasConceptScore W3202459445C52102323 @default.
- W3202459445 hasLocation W32024594451 @default.
- W3202459445 hasOpenAccess W3202459445 @default.
- W3202459445 hasPrimaryLocation W32024594451 @default.
- W3202459445 hasRelatedWork W1537622850 @default.
- W3202459445 hasRelatedWork W1988485990 @default.
- W3202459445 hasRelatedWork W2064877078 @default.
- W3202459445 hasRelatedWork W2154613448 @default.
- W3202459445 hasRelatedWork W2567319754 @default.
- W3202459445 hasRelatedWork W2931206373 @default.
- W3202459445 hasRelatedWork W3108980762 @default.
- W3202459445 hasRelatedWork W3206828132 @default.
- W3202459445 hasRelatedWork W4290774832 @default.
- W3202459445 hasRelatedWork W4306804934 @default.
- W3202459445 isParatext "false" @default.
- W3202459445 isRetracted "false" @default.
- W3202459445 magId "3202459445" @default.
- W3202459445 workType "article" @default.