Matches in SemOpenAlex for { <https://semopenalex.org/work/W3186228734> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3186228734 endingPage "32" @default.
- W3186228734 startingPage "26" @default.
- W3186228734 abstract "In this paper, we propose a simple yet effective method to represent point clouds as sets of samples drawn from a cloud-specific probability distribution. This interpretation matches intrinsic characteristics of point clouds: the number of points and their ordering within a cloud is not important as all points are drawn from the proximity of the object boundary. We postulate to represent each cloud as a parameterized probability distribution of points in space, which is defined by a generative neural network. The network operates by composing several spatial transformations of point locations. Once trained, it provides a natural framework for point cloud manipulation. For instance we can decouple cloud shape from its orientation and provide routines for aligning a new cloud into a default spatial orientation. To exploit similarities between same-class objects and to improve model performance, we turn to weight sharing: networks that model densities of points belonging to objects in the same family share all parameters with the exception of a small, object-specific embedding vector. We show that these embedding vectors capture semantic relationships between objects. Our method leverages generative invertible flow networks to learn embeddings as well as to generate point clouds. Thanks to this formulation and contrary to similar approaches, we are able to train our model in an end-to-end fashion. As a result, our model offers competitive or superior quantitative results on benchmark datasets, while enabling unprecedented capabilities to perform cloud manipulation tasks, such as point cloud registration and regeneration, by a generative network." @default.
- W3186228734 created "2021-08-02" @default.
- W3186228734 creator A5000408865 @default.
- W3186228734 creator A5010541429 @default.
- W3186228734 creator A5058169337 @default.
- W3186228734 creator A5070627781 @default.
- W3186228734 creator A5072966449 @default.
- W3186228734 creator A5083652196 @default.
- W3186228734 date "2021-10-01" @default.
- W3186228734 modified "2023-10-15" @default.
- W3186228734 title "Representing point clouds with generative conditional invertible flow networks" @default.
- W3186228734 cites W2085302753 @default.
- W3186228734 cites W2979750740 @default.
- W3186228734 doi "https://doi.org/10.1016/j.patrec.2021.07.001" @default.
- W3186228734 hasPublicationYear "2021" @default.
- W3186228734 type Work @default.
- W3186228734 sameAs 3186228734 @default.
- W3186228734 citedByCount "3" @default.
- W3186228734 countsByYear W31862287342021 @default.
- W3186228734 countsByYear W31862287342023 @default.
- W3186228734 crossrefType "journal-article" @default.
- W3186228734 hasAuthorship W3186228734A5000408865 @default.
- W3186228734 hasAuthorship W3186228734A5010541429 @default.
- W3186228734 hasAuthorship W3186228734A5058169337 @default.
- W3186228734 hasAuthorship W3186228734A5070627781 @default.
- W3186228734 hasAuthorship W3186228734A5072966449 @default.
- W3186228734 hasAuthorship W3186228734A5083652196 @default.
- W3186228734 hasBestOaLocation W31862287342 @default.
- W3186228734 hasConcept C111919701 @default.
- W3186228734 hasConcept C11413529 @default.
- W3186228734 hasConcept C131979681 @default.
- W3186228734 hasConcept C13280743 @default.
- W3186228734 hasConcept C154945302 @default.
- W3186228734 hasConcept C16345878 @default.
- W3186228734 hasConcept C165464430 @default.
- W3186228734 hasConcept C167966045 @default.
- W3186228734 hasConcept C185798385 @default.
- W3186228734 hasConcept C205649164 @default.
- W3186228734 hasConcept C2524010 @default.
- W3186228734 hasConcept C2781238097 @default.
- W3186228734 hasConcept C33923547 @default.
- W3186228734 hasConcept C39890363 @default.
- W3186228734 hasConcept C41008148 @default.
- W3186228734 hasConcept C41608201 @default.
- W3186228734 hasConcept C79974875 @default.
- W3186228734 hasConcept C80444323 @default.
- W3186228734 hasConceptScore W3186228734C111919701 @default.
- W3186228734 hasConceptScore W3186228734C11413529 @default.
- W3186228734 hasConceptScore W3186228734C131979681 @default.
- W3186228734 hasConceptScore W3186228734C13280743 @default.
- W3186228734 hasConceptScore W3186228734C154945302 @default.
- W3186228734 hasConceptScore W3186228734C16345878 @default.
- W3186228734 hasConceptScore W3186228734C165464430 @default.
- W3186228734 hasConceptScore W3186228734C167966045 @default.
- W3186228734 hasConceptScore W3186228734C185798385 @default.
- W3186228734 hasConceptScore W3186228734C205649164 @default.
- W3186228734 hasConceptScore W3186228734C2524010 @default.
- W3186228734 hasConceptScore W3186228734C2781238097 @default.
- W3186228734 hasConceptScore W3186228734C33923547 @default.
- W3186228734 hasConceptScore W3186228734C39890363 @default.
- W3186228734 hasConceptScore W3186228734C41008148 @default.
- W3186228734 hasConceptScore W3186228734C41608201 @default.
- W3186228734 hasConceptScore W3186228734C79974875 @default.
- W3186228734 hasConceptScore W3186228734C80444323 @default.
- W3186228734 hasFunder F4320308943 @default.
- W3186228734 hasFunder F4320322511 @default.
- W3186228734 hasFunder F4320325431 @default.
- W3186228734 hasLocation W31862287341 @default.
- W3186228734 hasLocation W31862287342 @default.
- W3186228734 hasOpenAccess W3186228734 @default.
- W3186228734 hasPrimaryLocation W31862287341 @default.
- W3186228734 hasRelatedWork W2280377497 @default.
- W3186228734 hasRelatedWork W2948437166 @default.
- W3186228734 hasRelatedWork W2963043971 @default.
- W3186228734 hasRelatedWork W3006036127 @default.
- W3186228734 hasRelatedWork W3039384219 @default.
- W3186228734 hasRelatedWork W4288334276 @default.
- W3186228734 hasRelatedWork W4304701012 @default.
- W3186228734 hasRelatedWork W4320342258 @default.
- W3186228734 hasRelatedWork W4320814215 @default.
- W3186228734 hasRelatedWork W4380558667 @default.
- W3186228734 hasVolume "150" @default.
- W3186228734 isParatext "false" @default.
- W3186228734 isRetracted "false" @default.
- W3186228734 magId "3186228734" @default.
- W3186228734 workType "article" @default.