FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312296985> ?p ?o ?g. }

• W4312296985 endingPage "34" @default.
• W4312296985 startingPage "19" @default.
• W4312296985 abstract "It is difficult to precisely annotate object instances and their semantics in 3D space, and as such, synthetic data are extensively used for these tasks, e.g., category-level 6D object pose and size estimation. However, the easy annotations in synthetic domains bring the downside effect of synthetic-to-real (Sim2Real) domain gap. In this work, we aim to address this issue in the task setting of Sim2Real, unsupervised domain adaptation for category-level 6D object pose and size estimation. We propose a method that is built upon a novel Deep Prior Deformation Network, shortened as DPDN. DPDN learns to deform features of categorical shape priors to match those of object observations, and is thus able to establish deep correspondence in the feature space for direct regression of object poses and sizes. To reduce the Sim2Real domain gap, we formulate a novel self-supervised objective upon DPDN via consistency learning; more specifically, we apply two rigid transformations to each object observation in parallel, and feed them into DPDN respectively to yield dual sets of predictions; on top of the parallel learning, an inter-consistency term is employed to keep cross consistency between dual predictions for improving the sensitivity of DPDN to pose changes, while individual intra-consistency ones are used to enforce self-adaptation within each learning itself. We train DPDN on both training sets of the synthetic CAMERA25 and real-world REAL275 datasets; our results outperform the existing methods on REAL275 test set under both the unsupervised and supervised settings. Ablation studies also verify the efficacy of our designs. Our code is released publicly at https://github.com/JiehongLin/Self-DPDN ." @default.
• W4312296985 created "2023-01-04" @default.
• W4312296985 creator A5003920944 @default.
• W4312296985 creator A5009929275 @default.
• W4312296985 creator A5038748720 @default.
• W4312296985 creator A5065964089 @default.
• W4312296985 date "2022-01-01" @default.
• W4312296985 modified "2023-09-26" @default.
• W4312296985 title "Category-Level 6D Object Pose and Size Estimation Using Self-supervised Deep Prior Deformation Networks" @default.
• W4312296985 cites W2122122381 @default.
• W4312296985 cites W2128019145 @default.
• W4312296985 cites W2139137304 @default.
• W4312296985 cites W2194775991 @default.
• W4312296985 cites W2555618208 @default.
• W4312296985 cites W2560023338 @default.
• W4312296985 cites W2949924544 @default.
• W4312296985 cites W2963150697 @default.
• W4312296985 cites W2963177347 @default.
• W4312296985 cites W2963892972 @default.
• W4312296985 cites W2979920800 @default.
• W4312296985 cites W2986303149 @default.
• W4312296985 cites W3004237909 @default.
• W4312296985 cites W3034986117 @default.
• W4312296985 cites W3095253761 @default.
• W4312296985 cites W3102758664 @default.
• W4312296985 cites W3107730598 @default.
• W4312296985 cites W3107992529 @default.
• W4312296985 cites W3163945288 @default.
• W4312296985 cites W3193686508 @default.
• W4312296985 cites W3202459445 @default.
• W4312296985 cites W3202538459 @default.
• W4312296985 cites W3214778407 @default.
• W4312296985 cites W4221167453 @default.
• W4312296985 cites W4312604533 @default.
• W4312296985 doi "https://doi.org/10.1007/978-3-031-20077-9_2" @default.
• W4312296985 hasPublicationYear "2022" @default.
• W4312296985 type Work @default.
• W4312296985 citedByCount "2" @default.
• W4312296985 countsByYear W43122969852023 @default.
• W4312296985 crossrefType "book-chapter" @default.
• W4312296985 hasAuthorship W4312296985A5003920944 @default.
• W4312296985 hasAuthorship W4312296985A5009929275 @default.
• W4312296985 hasAuthorship W4312296985A5038748720 @default.
• W4312296985 hasAuthorship W4312296985A5065964089 @default.
• W4312296985 hasBestOaLocation W43122969852 @default.
• W4312296985 hasConcept C107673813 @default.
• W4312296985 hasConcept C108583219 @default.
• W4312296985 hasConcept C119857082 @default.
• W4312296985 hasConcept C134306372 @default.
• W4312296985 hasConcept C136389625 @default.
• W4312296985 hasConcept C153180895 @default.
• W4312296985 hasConcept C154945302 @default.
• W4312296985 hasConcept C160920958 @default.
• W4312296985 hasConcept C177769412 @default.
• W4312296985 hasConcept C2776436953 @default.
• W4312296985 hasConcept C2781238097 @default.
• W4312296985 hasConcept C33923547 @default.
• W4312296985 hasConcept C36503486 @default.
• W4312296985 hasConcept C41008148 @default.
• W4312296985 hasConcept C50644808 @default.
• W4312296985 hasConcept C52102323 @default.
• W4312296985 hasConceptScore W4312296985C107673813 @default.
• W4312296985 hasConceptScore W4312296985C108583219 @default.
• W4312296985 hasConceptScore W4312296985C119857082 @default.
• W4312296985 hasConceptScore W4312296985C134306372 @default.
• W4312296985 hasConceptScore W4312296985C136389625 @default.
• W4312296985 hasConceptScore W4312296985C153180895 @default.
• W4312296985 hasConceptScore W4312296985C154945302 @default.
• W4312296985 hasConceptScore W4312296985C160920958 @default.
• W4312296985 hasConceptScore W4312296985C177769412 @default.
• W4312296985 hasConceptScore W4312296985C2776436953 @default.
• W4312296985 hasConceptScore W4312296985C2781238097 @default.
• W4312296985 hasConceptScore W4312296985C33923547 @default.
• W4312296985 hasConceptScore W4312296985C36503486 @default.
• W4312296985 hasConceptScore W4312296985C41008148 @default.
• W4312296985 hasConceptScore W4312296985C50644808 @default.
• W4312296985 hasConceptScore W4312296985C52102323 @default.
• W4312296985 hasLocation W43122969851 @default.
• W4312296985 hasLocation W43122969852 @default.
• W4312296985 hasOpenAccess W4312296985 @default.
• W4312296985 hasPrimaryLocation W43122969851 @default.
• W4312296985 hasRelatedWork W2127769904 @default.
• W4312296985 hasRelatedWork W2959141096 @default.
• W4312296985 hasRelatedWork W3192794374 @default.
• W4312296985 hasRelatedWork W4220686584 @default.
• W4312296985 hasRelatedWork W4223943233 @default.
• W4312296985 hasRelatedWork W4246751904 @default.
• W4312296985 hasRelatedWork W4312200629 @default.
• W4312296985 hasRelatedWork W4360585206 @default.
• W4312296985 hasRelatedWork W4364306694 @default.
• W4312296985 hasRelatedWork W4380075502 @default.
• W4312296985 isParatext "false" @default.
• W4312296985 isRetracted "false" @default.
• W4312296985 workType "book-chapter" @default.