Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366148220> ?p ?o ?g. }
- W4366148220 endingPage "3875" @default.
- W4366148220 startingPage "3868" @default.
- W4366148220 abstract "Transparent objects are a common part of daily life, but their unique optical properties make estimating their 6D pose a challenging task. In this letter, we propose TGF-Net, a monocular instance-level 6D pose estimation method for transparent objects based on geometric fusion. TGF-Net learns the edge features and surface fragments of transparent objects as intermediate features and reduces the influence of appearance changes on the 6D pose estimation of transparent objects by fusing rich geometric features in the network. Moreover, we propose an approach for generating high-fidelity large-scale synthetic datasets of transparent objects using Blender and use this approach to generate a synthetic dataset Trans6D-32 K. Trans6D-32 K contains rendered RGB images and poses information about transparent objects in a variety of different backgrounds, perspectives, and lighting conditions. To evaluate the performance of TGF-Net on 6D pose estimation of transparent objects, we compare with multiple related works on the dataset Trans6D-32 K. TGF-Net can be trained entirely on synthetic datasets without fine-tuning and applied directly to real-world scenarios. Multiple challenging real-scene experiments demonstrate the good performance of TGF-Net, while grasping experiments demonstrate the application value of TGF-Net in transparent object manipulation." @default.
- W4366148220 created "2023-04-19" @default.
- W4366148220 creator A5014423743 @default.
- W4366148220 creator A5019573103 @default.
- W4366148220 creator A5025660926 @default.
- W4366148220 creator A5076885280 @default.
- W4366148220 creator A5084510549 @default.
- W4366148220 creator A5091521146 @default.
- W4366148220 date "2023-06-01" @default.
- W4366148220 modified "2023-10-17" @default.
- W4366148220 title "TGF-Net: Sim2Real Transparent Object 6D Pose Estimation Based on Geometric Fusion" @default.
- W4366148220 cites W2194775991 @default.
- W4366148220 cites W2344474200 @default.
- W4366148220 cites W2487365028 @default.
- W4366148220 cites W2580726517 @default.
- W4366148220 cites W2604236302 @default.
- W4366148220 cites W2962783853 @default.
- W4366148220 cites W2962826264 @default.
- W4366148220 cites W2962914239 @default.
- W4366148220 cites W2963177347 @default.
- W4366148220 cites W2963756608 @default.
- W4366148220 cites W2964238416 @default.
- W4366148220 cites W2981378444 @default.
- W4366148220 cites W2989915422 @default.
- W4366148220 cites W2998787775 @default.
- W4366148220 cites W3007451651 @default.
- W4366148220 cites W3034268164 @default.
- W4366148220 cites W3034986117 @default.
- W4366148220 cites W3035235920 @default.
- W4366148220 cites W3035268949 @default.
- W4366148220 cites W3038023350 @default.
- W4366148220 cites W3089874271 @default.
- W4366148220 cites W3109733326 @default.
- W4366148220 cites W3156283702 @default.
- W4366148220 cites W3167542203 @default.
- W4366148220 cites W3171847116 @default.
- W4366148220 cites W3177069133 @default.
- W4366148220 cites W3189898414 @default.
- W4366148220 cites W3202305750 @default.
- W4366148220 cites W3207257716 @default.
- W4366148220 cites W4221167997 @default.
- W4366148220 cites W4225986028 @default.
- W4366148220 cites W4226029292 @default.
- W4366148220 cites W4285102159 @default.
- W4366148220 cites W4285102214 @default.
- W4366148220 cites W4285190019 @default.
- W4366148220 cites W4285505783 @default.
- W4366148220 cites W4312344659 @default.
- W4366148220 cites W4312876407 @default.
- W4366148220 doi "https://doi.org/10.1109/lra.2023.3268041" @default.
- W4366148220 hasPublicationYear "2023" @default.
- W4366148220 type Work @default.
- W4366148220 citedByCount "0" @default.
- W4366148220 crossrefType "journal-article" @default.
- W4366148220 hasAuthorship W4366148220A5014423743 @default.
- W4366148220 hasAuthorship W4366148220A5019573103 @default.
- W4366148220 hasAuthorship W4366148220A5025660926 @default.
- W4366148220 hasAuthorship W4366148220A5076885280 @default.
- W4366148220 hasAuthorship W4366148220A5084510549 @default.
- W4366148220 hasAuthorship W4366148220A5091521146 @default.
- W4366148220 hasConcept C14166107 @default.
- W4366148220 hasConcept C153180895 @default.
- W4366148220 hasConcept C154945302 @default.
- W4366148220 hasConcept C2524010 @default.
- W4366148220 hasConcept C2781238097 @default.
- W4366148220 hasConcept C31972630 @default.
- W4366148220 hasConcept C33923547 @default.
- W4366148220 hasConcept C41008148 @default.
- W4366148220 hasConcept C52102323 @default.
- W4366148220 hasConcept C65909025 @default.
- W4366148220 hasConcept C82990744 @default.
- W4366148220 hasConceptScore W4366148220C14166107 @default.
- W4366148220 hasConceptScore W4366148220C153180895 @default.
- W4366148220 hasConceptScore W4366148220C154945302 @default.
- W4366148220 hasConceptScore W4366148220C2524010 @default.
- W4366148220 hasConceptScore W4366148220C2781238097 @default.
- W4366148220 hasConceptScore W4366148220C31972630 @default.
- W4366148220 hasConceptScore W4366148220C33923547 @default.
- W4366148220 hasConceptScore W4366148220C41008148 @default.
- W4366148220 hasConceptScore W4366148220C52102323 @default.
- W4366148220 hasConceptScore W4366148220C65909025 @default.
- W4366148220 hasConceptScore W4366148220C82990744 @default.
- W4366148220 hasFunder F4320321001 @default.
- W4366148220 hasFunder F4320321543 @default.
- W4366148220 hasFunder F4320321921 @default.
- W4366148220 hasIssue "6" @default.
- W4366148220 hasLocation W43661482201 @default.
- W4366148220 hasOpenAccess W4366148220 @default.
- W4366148220 hasPrimaryLocation W43661482201 @default.
- W4366148220 hasRelatedWork W1988485990 @default.
- W4366148220 hasRelatedWork W2026349903 @default.
- W4366148220 hasRelatedWork W2144760288 @default.
- W4366148220 hasRelatedWork W2344839403 @default.
- W4366148220 hasRelatedWork W2891001608 @default.
- W4366148220 hasRelatedWork W2931206373 @default.
- W4366148220 hasRelatedWork W2956571887 @default.
- W4366148220 hasRelatedWork W3102636071 @default.
- W4366148220 hasRelatedWork W3108980762 @default.