Matches in SemOpenAlex for { <https://semopenalex.org/work/W3217458197> ?p ?o ?g. }
- W3217458197 abstract "Recently, category-level 6D object pose estimation has achieved significant improvements with the development of reconstructing canonical 3D representations. However, the reconstruction quality of existing methods is still far from excellent. In this paper, we propose a novel Adversarial Canonical Representation Reconstruction Network named ACR-Pose. ACR-Pose consists of a Reconstructor and a Discriminator. The Reconstructor is primarily composed of two novel sub-modules: Pose-Irrelevant Module (PIM) and Relational Reconstruction Module (RRM). PIM tends to learn canonical-related features to make the Reconstructor insensitive to rotation and translation, while RRM explores essential relational information between different input modalities to generate high-quality features. Subsequently, a Discriminator is employed to guide the Reconstructor to generate realistic canonical representations. The Reconstructor and the Discriminator learn to optimize through adversarial training. Experimental results on the prevalent NOCS-CAMERA and NOCS-REAL datasets demonstrate that our method achieves state-of-the-art performance." @default.
- W3217458197 created "2021-12-06" @default.
- W3217458197 creator A5010398730 @default.
- W3217458197 creator A5020455374 @default.
- W3217458197 creator A5021141988 @default.
- W3217458197 creator A5031166307 @default.
- W3217458197 creator A5066879163 @default.
- W3217458197 creator A5069101887 @default.
- W3217458197 creator A5082141047 @default.
- W3217458197 date "2021-11-20" @default.
- W3217458197 modified "2023-09-23" @default.
- W3217458197 title "ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimation" @default.
- W3217458197 cites W1820657498 @default.
- W3217458197 cites W2028936041 @default.
- W3217458197 cites W2041376653 @default.
- W3217458197 cites W2099471712 @default.
- W3217458197 cites W2119851068 @default.
- W3217458197 cites W2122122381 @default.
- W3217458197 cites W2125389028 @default.
- W3217458197 cites W2128019145 @default.
- W3217458197 cites W2194775991 @default.
- W3217458197 cites W2560023338 @default.
- W3217458197 cites W2739748921 @default.
- W3217458197 cites W2748217987 @default.
- W3217458197 cites W2768879211 @default.
- W3217458197 cites W2780046032 @default.
- W3217458197 cites W2796347433 @default.
- W3217458197 cites W2893763910 @default.
- W3217458197 cites W2895410314 @default.
- W3217458197 cites W2956121407 @default.
- W3217458197 cites W2962770929 @default.
- W3217458197 cites W2962783853 @default.
- W3217458197 cites W2962793481 @default.
- W3217458197 cites W2963150697 @default.
- W3217458197 cites W2963188159 @default.
- W3217458197 cites W2963231572 @default.
- W3217458197 cites W2963420686 @default.
- W3217458197 cites W2963756608 @default.
- W3217458197 cites W2963784072 @default.
- W3217458197 cites W2963892972 @default.
- W3217458197 cites W2964249569 @default.
- W3217458197 cites W2979750740 @default.
- W3217458197 cites W2981378444 @default.
- W3217458197 cites W2989915422 @default.
- W3217458197 cites W2997337685 @default.
- W3217458197 cites W3034597466 @default.
- W3217458197 cites W3034986117 @default.
- W3217458197 cites W3035172746 @default.
- W3217458197 cites W3035355652 @default.
- W3217458197 cites W3035551320 @default.
- W3217458197 cites W3092983688 @default.
- W3217458197 cites W3100052745 @default.
- W3217458197 cites W3107730598 @default.
- W3217458197 cites W3107992529 @default.
- W3217458197 cites W3108671865 @default.
- W3217458197 cites W3112108866 @default.
- W3217458197 cites W3133338337 @default.
- W3217458197 cites W3139887931 @default.
- W3217458197 cites W3144906546 @default.
- W3217458197 cites W3163945288 @default.
- W3217458197 cites W3168292752 @default.
- W3217458197 cites W3173744995 @default.
- W3217458197 cites W3179923621 @default.
- W3217458197 cites W3196328566 @default.
- W3217458197 cites W3198315345 @default.
- W3217458197 cites W3202538459 @default.
- W3217458197 doi "https://doi.org/10.48550/arxiv.2111.10524" @default.
- W3217458197 hasPublicationYear "2021" @default.
- W3217458197 type Work @default.
- W3217458197 sameAs 3217458197 @default.
- W3217458197 citedByCount "0" @default.
- W3217458197 crossrefType "posted-content" @default.
- W3217458197 hasAuthorship W3217458197A5010398730 @default.
- W3217458197 hasAuthorship W3217458197A5020455374 @default.
- W3217458197 hasAuthorship W3217458197A5021141988 @default.
- W3217458197 hasAuthorship W3217458197A5031166307 @default.
- W3217458197 hasAuthorship W3217458197A5066879163 @default.
- W3217458197 hasAuthorship W3217458197A5069101887 @default.
- W3217458197 hasAuthorship W3217458197A5082141047 @default.
- W3217458197 hasBestOaLocation W32174581971 @default.
- W3217458197 hasConcept C154945302 @default.
- W3217458197 hasConcept C17744445 @default.
- W3217458197 hasConcept C199539241 @default.
- W3217458197 hasConcept C2776359362 @default.
- W3217458197 hasConcept C2779803651 @default.
- W3217458197 hasConcept C2781238097 @default.
- W3217458197 hasConcept C31972630 @default.
- W3217458197 hasConcept C37736160 @default.
- W3217458197 hasConcept C41008148 @default.
- W3217458197 hasConcept C52102323 @default.
- W3217458197 hasConcept C74050887 @default.
- W3217458197 hasConcept C76155785 @default.
- W3217458197 hasConcept C94625758 @default.
- W3217458197 hasConcept C94915269 @default.
- W3217458197 hasConceptScore W3217458197C154945302 @default.
- W3217458197 hasConceptScore W3217458197C17744445 @default.
- W3217458197 hasConceptScore W3217458197C199539241 @default.
- W3217458197 hasConceptScore W3217458197C2776359362 @default.
- W3217458197 hasConceptScore W3217458197C2779803651 @default.
- W3217458197 hasConceptScore W3217458197C2781238097 @default.