Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312345105> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4312345105 abstract "Context information is important for instance segmentation on point clouds. Existing methods either only use local surroundings by stacking multiple convolution layers or use non-local methods to model long-range interactions. However, they usually directly operate on points which is an unstructured and low-level representation and is highly dependent on context. To address this issue, we propose an effective framework named Implicit-Part Context Aggregation (IPCA), which adopts implicit parts as an intermediate representation and achieves context aggregation through message passing along the implicit part graph. Specifically, we first organize unstructured points into geometrically consistent implicit parts and construct the implicit part graph according to the geometric adjacency. Then, an initial part embedding is extracted using the proposed Implicit Part Network (IPN) which can aggregate point features and capture the intrinsic geometric shape of the part. We further refine the part embedding by a graph reasoning module named Context Aggregation Network (CAN), which helps to make a more precise prediction by well exploiting the context information. Instance proposals are then generated by grouping implicit parts. Finally, we propose an additional step to attribute the entire instance proposal to a Semantic Criterion Net (SCN) to infer the semantics of the instance. The purpose is to correct the semantic prediction errors caused by not knowing the boundary and overall shape of the object in the previous steps. Extensive experiments on two large datasets, ScanNet and 3RScan, demonstrate the effectiveness of our method. To our knowledge, it yields the highest performance on the ScanNet test benchmark and its AP@50 is 9.5 points higher than the baseline. The code is available at https://github.com/xiaodongww/IPCA" @default.
- W4312345105 created "2023-01-04" @default.
- W4312345105 creator A5079114418 @default.
- W4312345105 creator A5083420537 @default.
- W4312345105 creator A5090788010 @default.
- W4312345105 date "2022-10-23" @default.
- W4312345105 modified "2023-10-16" @default.
- W4312345105 title "Implicit-Part Based Context Aggregation for Point Cloud Instance Segmentation" @default.
- W4312345105 cites W1999478155 @default.
- W4312345105 cites W2049776679 @default.
- W4312345105 cites W2123893263 @default.
- W4312345105 cites W2156406284 @default.
- W4312345105 cites W2594519801 @default.
- W4312345105 cites W2769312834 @default.
- W4312345105 cites W2904332125 @default.
- W4312345105 cites W2910490344 @default.
- W4312345105 cites W2959771705 @default.
- W4312345105 cites W2962759414 @default.
- W4312345105 cites W2963150697 @default.
- W4312345105 cites W2963182550 @default.
- W4312345105 cites W2963281829 @default.
- W4312345105 cites W2963587345 @default.
- W4312345105 cites W2963857746 @default.
- W4312345105 cites W2964266557 @default.
- W4312345105 cites W2981422075 @default.
- W4312345105 cites W2988715931 @default.
- W4312345105 cites W2995182785 @default.
- W4312345105 cites W3004300126 @default.
- W4312345105 cites W3034430142 @default.
- W4312345105 cites W3034550906 @default.
- W4312345105 cites W3034949383 @default.
- W4312345105 cites W3044856323 @default.
- W4312345105 cites W3170500059 @default.
- W4312345105 cites W3178663471 @default.
- W4312345105 cites W3204034406 @default.
- W4312345105 cites W4214773923 @default.
- W4312345105 doi "https://doi.org/10.1109/iros47612.2022.9981772" @default.
- W4312345105 hasPublicationYear "2022" @default.
- W4312345105 type Work @default.
- W4312345105 citedByCount "0" @default.
- W4312345105 crossrefType "proceedings-article" @default.
- W4312345105 hasAuthorship W4312345105A5079114418 @default.
- W4312345105 hasAuthorship W4312345105A5083420537 @default.
- W4312345105 hasAuthorship W4312345105A5090788010 @default.
- W4312345105 hasConcept C110484373 @default.
- W4312345105 hasConcept C11413529 @default.
- W4312345105 hasConcept C131979681 @default.
- W4312345105 hasConcept C132525143 @default.
- W4312345105 hasConcept C151730666 @default.
- W4312345105 hasConcept C154945302 @default.
- W4312345105 hasConcept C17744445 @default.
- W4312345105 hasConcept C199539241 @default.
- W4312345105 hasConcept C2776359362 @default.
- W4312345105 hasConcept C2779343474 @default.
- W4312345105 hasConcept C41008148 @default.
- W4312345105 hasConcept C41608201 @default.
- W4312345105 hasConcept C80444323 @default.
- W4312345105 hasConcept C86803240 @default.
- W4312345105 hasConcept C89600930 @default.
- W4312345105 hasConcept C94625758 @default.
- W4312345105 hasConceptScore W4312345105C110484373 @default.
- W4312345105 hasConceptScore W4312345105C11413529 @default.
- W4312345105 hasConceptScore W4312345105C131979681 @default.
- W4312345105 hasConceptScore W4312345105C132525143 @default.
- W4312345105 hasConceptScore W4312345105C151730666 @default.
- W4312345105 hasConceptScore W4312345105C154945302 @default.
- W4312345105 hasConceptScore W4312345105C17744445 @default.
- W4312345105 hasConceptScore W4312345105C199539241 @default.
- W4312345105 hasConceptScore W4312345105C2776359362 @default.
- W4312345105 hasConceptScore W4312345105C2779343474 @default.
- W4312345105 hasConceptScore W4312345105C41008148 @default.
- W4312345105 hasConceptScore W4312345105C41608201 @default.
- W4312345105 hasConceptScore W4312345105C80444323 @default.
- W4312345105 hasConceptScore W4312345105C86803240 @default.
- W4312345105 hasConceptScore W4312345105C89600930 @default.
- W4312345105 hasConceptScore W4312345105C94625758 @default.
- W4312345105 hasLocation W43123451051 @default.
- W4312345105 hasOpenAccess W4312345105 @default.
- W4312345105 hasPrimaryLocation W43123451051 @default.
- W4312345105 hasRelatedWork W2893186803 @default.
- W4312345105 hasRelatedWork W2923818335 @default.
- W4312345105 hasRelatedWork W3035116611 @default.
- W4312345105 hasRelatedWork W3044354590 @default.
- W4312345105 hasRelatedWork W3094605108 @default.
- W4312345105 hasRelatedWork W4212923699 @default.
- W4312345105 hasRelatedWork W4226361842 @default.
- W4312345105 hasRelatedWork W4287763734 @default.
- W4312345105 hasRelatedWork W4310879833 @default.
- W4312345105 hasRelatedWork W89898052 @default.
- W4312345105 isParatext "false" @default.
- W4312345105 isRetracted "false" @default.
- W4312345105 workType "article" @default.