FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3184699107> ?p ?o ?g. }

• W3184699107 abstract "6D pose estimation of rigid objects from a single RGB image has seen tremendous improvements recently by using deep learning to combat complex real-world variations, but a majority of methods build models on the per-object level, failing to scale to multiple objects simultaneously. In this paper, we present a novel approach for scalable 6D pose estimation, by self-supervised learning on synthetic data of multiple objects using a single autoencoder. To handle multiple objects and generalize to unseen objects, we disentangle the latent object shape and pose representations, so that the latent shape space models shape similarities, and the latent pose code is used for rotation retrieval by comparison with canonical rotations. To encourage shape space construction, we apply contrastive metric learning and enable the processing of unseen objects by referring to similar training objects. The different symmetries across objects induce inconsistent latent pose spaces, which we capture with a conditioned block producing shape-dependent pose codebooks by re-entangling shape and pose representations. We test our method on two multi-object benchmarks with real data, T-LESS and NOCS REAL275, and show it outperforms existing RGB-based methods in terms of pose estimation accuracy and generalization." @default.
• W3184699107 created "2021-08-02" @default.
• W3184699107 creator A5014324841 @default.
• W3184699107 creator A5017191249 @default.
• W3184699107 creator A5031194653 @default.
• W3184699107 creator A5033764099 @default.
• W3184699107 creator A5052267876 @default.
• W3184699107 creator A5056602636 @default.
• W3184699107 creator A5089968146 @default.
• W3184699107 date "2021-07-27" @default.
• W3184699107 modified "2023-10-01" @default.
• W3184699107 title "Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation." @default.
• W3184699107 cites W1522301498 @default.
• W3184699107 cites W1526868886 @default.
• W3184699107 cites W2016427216 @default.
• W3184699107 cites W2096509866 @default.
• W3184699107 cites W2163922914 @default.
• W3184699107 cites W2170653751 @default.
• W3184699107 cites W2190691619 @default.
• W3184699107 cites W2472269674 @default.
• W3184699107 cites W2580726517 @default.
• W3184699107 cites W2604236302 @default.
• W3184699107 cites W2753738274 @default.
• W3184699107 cites W2798991696 @default.
• W3184699107 cites W2842511635 @default.
• W3184699107 cites W2888456631 @default.
• W3184699107 cites W2888752296 @default.
• W3184699107 cites W2891001608 @default.
• W3184699107 cites W2895439318 @default.
• W3184699107 cites W2902476877 @default.
• W3184699107 cites W2903145553 @default.
• W3184699107 cites W2903538854 @default.
• W3184699107 cites W2961443823 @default.
• W3184699107 cites W2963150697 @default.
• W3184699107 cites W2963188159 @default.
• W3184699107 cites W2963226019 @default.
• W3184699107 cites W2963351448 @default.
• W3184699107 cites W2963403868 @default.
• W3184699107 cites W2963756608 @default.
• W3184699107 cites W2963892972 @default.
• W3184699107 cites W2968930673 @default.
• W3184699107 cites W2981854237 @default.
• W3184699107 cites W2982683587 @default.
• W3184699107 cites W2989701728 @default.
• W3184699107 cites W3034573608 @default.
• W3184699107 cites W3034597466 @default.
• W3184699107 cites W3034978746 @default.
• W3184699107 cites W3035524453 @default.
• W3184699107 cites W3035574324 @default.
• W3184699107 cites W3035630023 @default.
• W3184699107 cites W3037805286 @default.
• W3184699107 cites W3038023350 @default.
• W3184699107 cites W3040869941 @default.
• W3184699107 cites W3091899207 @default.
• W3184699107 cites W3100052745 @default.
• W3184699107 cites W3102636071 @default.
• W3184699107 cites W3106546328 @default.
• W3184699107 cites W3107372911 @default.
• W3184699107 cites W3107992529 @default.
• W3184699107 cites W3127298196 @default.
• W3184699107 hasPublicationYear "2021" @default.
• W3184699107 type Work @default.
• W3184699107 sameAs 3184699107 @default.
• W3184699107 citedByCount "0" @default.
• W3184699107 crossrefType "posted-content" @default.
• W3184699107 hasAuthorship W3184699107A5014324841 @default.
• W3184699107 hasAuthorship W3184699107A5017191249 @default.
• W3184699107 hasAuthorship W3184699107A5031194653 @default.
• W3184699107 hasAuthorship W3184699107A5033764099 @default.
• W3184699107 hasAuthorship W3184699107A5052267876 @default.
• W3184699107 hasAuthorship W3184699107A5056602636 @default.
• W3184699107 hasAuthorship W3184699107A5089968146 @default.
• W3184699107 hasConcept C101738243 @default.
• W3184699107 hasConcept C108583219 @default.
• W3184699107 hasConcept C111919701 @default.
• W3184699107 hasConcept C119857082 @default.
• W3184699107 hasConcept C134306372 @default.
• W3184699107 hasConcept C153180895 @default.
• W3184699107 hasConcept C154945302 @default.
• W3184699107 hasConcept C177148314 @default.
• W3184699107 hasConcept C2524010 @default.
• W3184699107 hasConcept C2777210771 @default.
• W3184699107 hasConcept C2778572836 @default.
• W3184699107 hasConcept C2781238097 @default.
• W3184699107 hasConcept C31972630 @default.
• W3184699107 hasConcept C33923547 @default.
• W3184699107 hasConcept C41008148 @default.
• W3184699107 hasConcept C48044578 @default.
• W3184699107 hasConcept C52102323 @default.
• W3184699107 hasConcept C74050887 @default.
• W3184699107 hasConcept C77088390 @default.
• W3184699107 hasConcept C82990744 @default.
• W3184699107 hasConceptScore W3184699107C101738243 @default.
• W3184699107 hasConceptScore W3184699107C108583219 @default.
• W3184699107 hasConceptScore W3184699107C111919701 @default.
• W3184699107 hasConceptScore W3184699107C119857082 @default.
• W3184699107 hasConceptScore W3184699107C134306372 @default.
• W3184699107 hasConceptScore W3184699107C153180895 @default.
• W3184699107 hasConceptScore W3184699107C154945302 @default.
• W3184699107 hasConceptScore W3184699107C177148314 @default.

• next