Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306175945> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4306175945 abstract "Establishment of point correspondence between camera and object coordinate systems is a promising way to solve 6D object poses. However, surrogate objectives of correspondence learning in 3D space are a step away from the true ones of object pose estimation, making the learning suboptimal for the end task. In this paper, we address this shortcoming by introducing a new method of Deep Correspondence Learning Network for direct 6D object pose estimation, shortened as DCL-Net. Specifically, DCL-Net employs dual newly proposed Feature Disengagement and Alignment (FDA) modules to establish, in the feature space, partial-to-partial correspondence and complete-to-complete one for partial object observation and its complete CAD model, respectively, which result in aggregated pose and match feature pairs from two coordinate systems; these two FDA modules thus bring complementary advantages. The match feature pairs are used to learn confidence scores for measuring the qualities of deep correspondence, while the pose feature pairs are weighted by confidence scores for direct object pose regression. A confidence-based pose refinement network is also proposed to further improve pose precision in an iterative manner. Extensive experiments show that DCL-Net outperforms existing methods on three benchmarking datasets, including YCB-Video, LineMOD, and Oclussion-LineMOD; ablation studies also confirm the efficacy of our novel designs." @default.
- W4306175945 created "2022-10-14" @default.
- W4306175945 creator A5003920944 @default.
- W4306175945 creator A5065964089 @default.
- W4306175945 creator A5083095344 @default.
- W4306175945 date "2022-10-11" @default.
- W4306175945 modified "2023-09-27" @default.
- W4306175945 title "DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation" @default.
- W4306175945 doi "https://doi.org/10.48550/arxiv.2210.05232" @default.
- W4306175945 hasPublicationYear "2022" @default.
- W4306175945 type Work @default.
- W4306175945 citedByCount "0" @default.
- W4306175945 crossrefType "posted-content" @default.
- W4306175945 hasAuthorship W4306175945A5003920944 @default.
- W4306175945 hasAuthorship W4306175945A5065964089 @default.
- W4306175945 hasAuthorship W4306175945A5083095344 @default.
- W4306175945 hasBestOaLocation W43061759451 @default.
- W4306175945 hasConcept C108583219 @default.
- W4306175945 hasConcept C119857082 @default.
- W4306175945 hasConcept C138885662 @default.
- W4306175945 hasConcept C144133560 @default.
- W4306175945 hasConcept C153180895 @default.
- W4306175945 hasConcept C154945302 @default.
- W4306175945 hasConcept C162853370 @default.
- W4306175945 hasConcept C2776401178 @default.
- W4306175945 hasConcept C2781238097 @default.
- W4306175945 hasConcept C31972630 @default.
- W4306175945 hasConcept C36613465 @default.
- W4306175945 hasConcept C41008148 @default.
- W4306175945 hasConcept C41895202 @default.
- W4306175945 hasConcept C52102323 @default.
- W4306175945 hasConcept C83665646 @default.
- W4306175945 hasConcept C86251818 @default.
- W4306175945 hasConceptScore W4306175945C108583219 @default.
- W4306175945 hasConceptScore W4306175945C119857082 @default.
- W4306175945 hasConceptScore W4306175945C138885662 @default.
- W4306175945 hasConceptScore W4306175945C144133560 @default.
- W4306175945 hasConceptScore W4306175945C153180895 @default.
- W4306175945 hasConceptScore W4306175945C154945302 @default.
- W4306175945 hasConceptScore W4306175945C162853370 @default.
- W4306175945 hasConceptScore W4306175945C2776401178 @default.
- W4306175945 hasConceptScore W4306175945C2781238097 @default.
- W4306175945 hasConceptScore W4306175945C31972630 @default.
- W4306175945 hasConceptScore W4306175945C36613465 @default.
- W4306175945 hasConceptScore W4306175945C41008148 @default.
- W4306175945 hasConceptScore W4306175945C41895202 @default.
- W4306175945 hasConceptScore W4306175945C52102323 @default.
- W4306175945 hasConceptScore W4306175945C83665646 @default.
- W4306175945 hasConceptScore W4306175945C86251818 @default.
- W4306175945 hasLocation W43061759451 @default.
- W4306175945 hasOpenAccess W4306175945 @default.
- W4306175945 hasPrimaryLocation W43061759451 @default.
- W4306175945 hasRelatedWork W1537622850 @default.
- W4306175945 hasRelatedWork W2026349903 @default.
- W4306175945 hasRelatedWork W2166024367 @default.
- W4306175945 hasRelatedWork W2544359817 @default.
- W4306175945 hasRelatedWork W2556085923 @default.
- W4306175945 hasRelatedWork W2636771212 @default.
- W4306175945 hasRelatedWork W2956571887 @default.
- W4306175945 hasRelatedWork W3108980762 @default.
- W4306175945 hasRelatedWork W4377833916 @default.
- W4306175945 hasRelatedWork W62482549 @default.
- W4306175945 isParatext "false" @default.
- W4306175945 isRetracted "false" @default.
- W4306175945 workType "article" @default.