Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385431079> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4385431079 endingPage "621" @default.
- W4385431079 startingPage "609" @default.
- W4385431079 abstract "Category-level object pose estimation aims to predict the 6D object pose and size of arbitrary objects from known categories. It remains a challenge due to the large intra-class shape variation. Recently, the introduction of the shape prior adaptation mechanism into the normalized canonical coordinates (i.e., NOCS) reconstruction process has been shown to be effective in mitigating the intra-class shape variation. However, existing shape prior adaptation methods simply map the observed point cloud to the normalized object space, and the extracted object descriptors are not sufficient for the perception of the object pose. As a result, they fail to predict the pose of objects with complex geometric structures (e.g., cameras). To this end, this paper proposes a novel shape prior adaption method named MSSPA-GC for category-level object pose estimation. Specifically, our main network takes the observed instance point cloud converted from the RGB-D image and the prior shape point cloud pre-trained on the object CAD models as inputs. Then, a novel 3D graph convolution network and a PointNet-like MLP network are designed to extract pose-aware object features and shape-aware object features from these two inputs, respectively. After that, the two-stream object features are aggregated through a multi-scale feature propagation mechanism to generate comprehensive 3D object descriptors that maintain both pose-sensitive geometric stability and intra-class shape consistency. Finally, by leveraging object descriptors aware of both object pose and shape when reconstructing the NOCS coordinates, our approach elegantly achieves state-of-the-art performance on the widely used REAL275 and CAMERA25 datasets using only 25% of the parameters compared with existing shape prior adaptation models. Moreover, our method also exhibits decent generalization ability on the unconstrained REDWOOD75 dataset." @default.
- W4385431079 created "2023-08-01" @default.
- W4385431079 creator A5017524281 @default.
- W4385431079 creator A5030516439 @default.
- W4385431079 creator A5051365167 @default.
- W4385431079 creator A5084538628 @default.
- W4385431079 date "2023-09-01" @default.
- W4385431079 modified "2023-10-14" @default.
- W4385431079 title "MSSPA-GC: Multi-Scale Shape Prior Adaptation with 3D Graph Convolutions for Category-Level Object Pose Estimation" @default.
- W4385431079 cites W1991544872 @default.
- W4385431079 cites W2085261163 @default.
- W4385431079 cites W2128019145 @default.
- W4385431079 cites W2963150697 @default.
- W4385431079 cites W2963177347 @default.
- W4385431079 cites W2963756608 @default.
- W4385431079 cites W2963892972 @default.
- W4385431079 cites W2964249569 @default.
- W4385431079 cites W2989915422 @default.
- W4385431079 cites W3034597466 @default.
- W4385431079 cites W3034712732 @default.
- W4385431079 cites W3034986117 @default.
- W4385431079 cites W3035398346 @default.
- W4385431079 cites W3163945288 @default.
- W4385431079 cites W3179923621 @default.
- W4385431079 cites W3196328566 @default.
- W4385431079 cites W3202459445 @default.
- W4385431079 cites W3202538459 @default.
- W4385431079 cites W3214778407 @default.
- W4385431079 cites W4312604533 @default.
- W4385431079 doi "https://doi.org/10.1016/j.neunet.2023.07.037" @default.
- W4385431079 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37597505" @default.
- W4385431079 hasPublicationYear "2023" @default.
- W4385431079 type Work @default.
- W4385431079 citedByCount "0" @default.
- W4385431079 crossrefType "journal-article" @default.
- W4385431079 hasAuthorship W4385431079A5017524281 @default.
- W4385431079 hasAuthorship W4385431079A5030516439 @default.
- W4385431079 hasAuthorship W4385431079A5051365167 @default.
- W4385431079 hasAuthorship W4385431079A5084538628 @default.
- W4385431079 hasConcept C129641003 @default.
- W4385431079 hasConcept C131979681 @default.
- W4385431079 hasConcept C132525143 @default.
- W4385431079 hasConcept C153180895 @default.
- W4385431079 hasConcept C154945302 @default.
- W4385431079 hasConcept C22100474 @default.
- W4385431079 hasConcept C2781238097 @default.
- W4385431079 hasConcept C31972630 @default.
- W4385431079 hasConcept C36613465 @default.
- W4385431079 hasConcept C41008148 @default.
- W4385431079 hasConcept C52102323 @default.
- W4385431079 hasConcept C64876066 @default.
- W4385431079 hasConcept C80444323 @default.
- W4385431079 hasConcept C89600930 @default.
- W4385431079 hasConceptScore W4385431079C129641003 @default.
- W4385431079 hasConceptScore W4385431079C131979681 @default.
- W4385431079 hasConceptScore W4385431079C132525143 @default.
- W4385431079 hasConceptScore W4385431079C153180895 @default.
- W4385431079 hasConceptScore W4385431079C154945302 @default.
- W4385431079 hasConceptScore W4385431079C22100474 @default.
- W4385431079 hasConceptScore W4385431079C2781238097 @default.
- W4385431079 hasConceptScore W4385431079C31972630 @default.
- W4385431079 hasConceptScore W4385431079C36613465 @default.
- W4385431079 hasConceptScore W4385431079C41008148 @default.
- W4385431079 hasConceptScore W4385431079C52102323 @default.
- W4385431079 hasConceptScore W4385431079C64876066 @default.
- W4385431079 hasConceptScore W4385431079C80444323 @default.
- W4385431079 hasConceptScore W4385431079C89600930 @default.
- W4385431079 hasFunder F4320321001 @default.
- W4385431079 hasFunder F4320335777 @default.
- W4385431079 hasLocation W43854310791 @default.
- W4385431079 hasLocation W43854310792 @default.
- W4385431079 hasOpenAccess W4385431079 @default.
- W4385431079 hasPrimaryLocation W43854310791 @default.
- W4385431079 hasRelatedWork W1968783203 @default.
- W4385431079 hasRelatedWork W2088028039 @default.
- W4385431079 hasRelatedWork W2148535645 @default.
- W4385431079 hasRelatedWork W2798721181 @default.
- W4385431079 hasRelatedWork W2946083937 @default.
- W4385431079 hasRelatedWork W2951583186 @default.
- W4385431079 hasRelatedWork W4206633503 @default.
- W4385431079 hasRelatedWork W4299867837 @default.
- W4385431079 hasRelatedWork W4382141741 @default.
- W4385431079 hasRelatedWork W4386075737 @default.
- W4385431079 hasVolume "166" @default.
- W4385431079 isParatext "false" @default.
- W4385431079 isRetracted "false" @default.
- W4385431079 workType "article" @default.