Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285221346> ?p ?o ?g. }
- W4285221346 endingPage "8987" @default.
- W4285221346 startingPage "8980" @default.
- W4285221346 abstract "Estimating the 6DOF pose of objects is an important function in many applications, such as robot manipulation or augmented reality. However, accurate and fast pose estimation from 3D point clouds is challenging, because of the complexity of object shapes, measurement noise, and presence of occlusions. We address this challenging task using an end-to-end learning approach for object pose estimation given a raw point cloud input. Our architecture pools geometric features together using a self-attention mechanism and adopts a deep Hough voting scheme for pose proposal generation. To build robustness to occlusion, the proposed network generates candidates by casting votes and accumulating evidence for object locations. Specifically, our model learns higher-level features by leveraging the dependency of object parts and object instances, thereby boosting the performance of object pose estimation. Our experiments show that our method outperforms state-of-the-art approaches in public benchmarks including the Siléane dataset [35 and the Fraunhofer IPA dataset [36]. We also deploy our proposed method to a real robot pick-and-place based on the estimated pose." @default.
- W4285221346 created "2022-07-14" @default.
- W4285221346 creator A5009421795 @default.
- W4285221346 creator A5023785357 @default.
- W4285221346 creator A5044352907 @default.
- W4285221346 date "2022-10-01" @default.
- W4285221346 modified "2023-10-14" @default.
- W4285221346 title "Voting and Attention-Based Pose Relation Learning for Object Pose Estimation From 3D Point Clouds" @default.
- W4285221346 cites W1881711072 @default.
- W4285221346 cites W2007200979 @default.
- W4285221346 cites W2033574012 @default.
- W4285221346 cites W2041469568 @default.
- W4285221346 cites W2052789223 @default.
- W4285221346 cites W2063463366 @default.
- W4285221346 cites W2097073572 @default.
- W4285221346 cites W2161168419 @default.
- W4285221346 cites W2180507191 @default.
- W4285221346 cites W2766736793 @default.
- W4285221346 cites W2949924544 @default.
- W4285221346 cites W2955058313 @default.
- W4285221346 cites W2963091558 @default.
- W4285221346 cites W2963177347 @default.
- W4285221346 cites W2963954913 @default.
- W4285221346 cites W2964110616 @default.
- W4285221346 cites W2983446232 @default.
- W4285221346 cites W2988715931 @default.
- W4285221346 cites W2989915422 @default.
- W4285221346 cites W3003215308 @default.
- W4285221346 cites W3009254297 @default.
- W4285221346 cites W3034986117 @default.
- W4285221346 cites W3035268949 @default.
- W4285221346 cites W3089668137 @default.
- W4285221346 cites W3091481715 @default.
- W4285221346 cites W3100052745 @default.
- W4285221346 cites W3100901148 @default.
- W4285221346 cites W3101102451 @default.
- W4285221346 cites W3163527364 @default.
- W4285221346 cites W3176437888 @default.
- W4285221346 doi "https://doi.org/10.1109/lra.2022.3189158" @default.
- W4285221346 hasPublicationYear "2022" @default.
- W4285221346 type Work @default.
- W4285221346 citedByCount "2" @default.
- W4285221346 countsByYear W42852213462023 @default.
- W4285221346 crossrefType "journal-article" @default.
- W4285221346 hasAuthorship W4285221346A5009421795 @default.
- W4285221346 hasAuthorship W4285221346A5023785357 @default.
- W4285221346 hasAuthorship W4285221346A5044352907 @default.
- W4285221346 hasBestOaLocation W42852213461 @default.
- W4285221346 hasConcept C104317684 @default.
- W4285221346 hasConcept C131979681 @default.
- W4285221346 hasConcept C153180895 @default.
- W4285221346 hasConcept C154945302 @default.
- W4285221346 hasConcept C17744445 @default.
- W4285221346 hasConcept C185592680 @default.
- W4285221346 hasConcept C199539241 @default.
- W4285221346 hasConcept C22100474 @default.
- W4285221346 hasConcept C2776151529 @default.
- W4285221346 hasConcept C2781238097 @default.
- W4285221346 hasConcept C31972630 @default.
- W4285221346 hasConcept C36613465 @default.
- W4285221346 hasConcept C41008148 @default.
- W4285221346 hasConcept C46686674 @default.
- W4285221346 hasConcept C520049643 @default.
- W4285221346 hasConcept C52102323 @default.
- W4285221346 hasConcept C55493867 @default.
- W4285221346 hasConcept C63479239 @default.
- W4285221346 hasConcept C94625758 @default.
- W4285221346 hasConceptScore W4285221346C104317684 @default.
- W4285221346 hasConceptScore W4285221346C131979681 @default.
- W4285221346 hasConceptScore W4285221346C153180895 @default.
- W4285221346 hasConceptScore W4285221346C154945302 @default.
- W4285221346 hasConceptScore W4285221346C17744445 @default.
- W4285221346 hasConceptScore W4285221346C185592680 @default.
- W4285221346 hasConceptScore W4285221346C199539241 @default.
- W4285221346 hasConceptScore W4285221346C22100474 @default.
- W4285221346 hasConceptScore W4285221346C2776151529 @default.
- W4285221346 hasConceptScore W4285221346C2781238097 @default.
- W4285221346 hasConceptScore W4285221346C31972630 @default.
- W4285221346 hasConceptScore W4285221346C36613465 @default.
- W4285221346 hasConceptScore W4285221346C41008148 @default.
- W4285221346 hasConceptScore W4285221346C46686674 @default.
- W4285221346 hasConceptScore W4285221346C520049643 @default.
- W4285221346 hasConceptScore W4285221346C52102323 @default.
- W4285221346 hasConceptScore W4285221346C55493867 @default.
- W4285221346 hasConceptScore W4285221346C63479239 @default.
- W4285221346 hasConceptScore W4285221346C94625758 @default.
- W4285221346 hasIssue "4" @default.
- W4285221346 hasLocation W42852213461 @default.
- W4285221346 hasOpenAccess W4285221346 @default.
- W4285221346 hasPrimaryLocation W42852213461 @default.
- W4285221346 hasRelatedWork W1537622850 @default.
- W4285221346 hasRelatedWork W1968716783 @default.
- W4285221346 hasRelatedWork W1988485990 @default.
- W4285221346 hasRelatedWork W2033672678 @default.
- W4285221346 hasRelatedWork W2127769904 @default.
- W4285221346 hasRelatedWork W2128635338 @default.
- W4285221346 hasRelatedWork W2129348295 @default.
- W4285221346 hasRelatedWork W2567319754 @default.