Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949671016> ?p ?o ?g. }
- W2949671016 abstract "Three-dimensional geometric data offer an excellent domain for studying representation learning and generative modeling. In this paper, we look at geometric data represented as point clouds. We introduce a deep AutoEncoder (AE) network with state-of-the-art reconstruction quality and generalization ability. The learned representations outperform existing methods on 3D recognition tasks and enable shape editing via simple algebraic manipulations, such as semantic part editing, shape analogies and shape interpolation, as well as shape completion. We perform a thorough study of different generative models including GANs operating on the raw point clouds, significantly improved GANs trained in the fixed latent space of our AEs, and Gaussian Mixture Models (GMMs). To quantitatively evaluate generative models we introduce measures of sample fidelity and diversity based on matchings between sets of point clouds. Interestingly, our evaluation of generalization, fidelity and diversity reveals that GMMs trained in the latent space of our AEs yield the best results overall." @default.
- W2949671016 created "2019-06-27" @default.
- W2949671016 creator A5005467474 @default.
- W2949671016 creator A5038007540 @default.
- W2949671016 creator A5065368881 @default.
- W2949671016 creator A5088076429 @default.
- W2949671016 date "2017-07-08" @default.
- W2949671016 modified "2023-09-27" @default.
- W2949671016 title "Learning Representations and Generative Models for 3D Point Clouds" @default.
- W2949671016 cites W1498436455 @default.
- W2949671016 cites W1561952261 @default.
- W2949671016 cites W1781857629 @default.
- W2949671016 cites W1920022804 @default.
- W2949671016 cites W2001353114 @default.
- W2949671016 cites W2014667763 @default.
- W2949671016 cites W2021122545 @default.
- W2949671016 cites W2099471712 @default.
- W2949671016 cites W2143668817 @default.
- W2949671016 cites W2190691619 @default.
- W2949671016 cites W2210838531 @default.
- W2949671016 cites W2335364074 @default.
- W2949671016 cites W2338532005 @default.
- W2949671016 cites W2432004435 @default.
- W2949671016 cites W2511691466 @default.
- W2949671016 cites W2553307952 @default.
- W2949671016 cites W2553913815 @default.
- W2949671016 cites W2556467266 @default.
- W2949671016 cites W2560609797 @default.
- W2949671016 cites W2581617186 @default.
- W2949671016 cites W2585630030 @default.
- W2949671016 cites W2603429625 @default.
- W2949671016 cites W2632772789 @default.
- W2949671016 cites W2746892480 @default.
- W2949671016 cites W2784996692 @default.
- W2949671016 cites W2949070976 @default.
- W2949671016 cites W2950133940 @default.
- W2949671016 cites W2950292946 @default.
- W2949671016 cites W2950821630 @default.
- W2949671016 cites W2951004968 @default.
- W2949671016 cites W2951140085 @default.
- W2949671016 cites W2952789225 @default.
- W2949671016 cites W2962865163 @default.
- W2949671016 cites W2963121255 @default.
- W2949671016 cites W2964121744 @default.
- W2949671016 cites W2964321699 @default.
- W2949671016 cites W637153065 @default.
- W2949671016 hasPublicationYear "2017" @default.
- W2949671016 type Work @default.
- W2949671016 sameAs 2949671016 @default.
- W2949671016 citedByCount "62" @default.
- W2949671016 countsByYear W29496710162017 @default.
- W2949671016 countsByYear W29496710162018 @default.
- W2949671016 countsByYear W29496710162019 @default.
- W2949671016 countsByYear W29496710162020 @default.
- W2949671016 countsByYear W29496710162021 @default.
- W2949671016 crossrefType "posted-content" @default.
- W2949671016 hasAuthorship W2949671016A5005467474 @default.
- W2949671016 hasAuthorship W2949671016A5038007540 @default.
- W2949671016 hasAuthorship W2949671016A5065368881 @default.
- W2949671016 hasAuthorship W2949671016A5088076429 @default.
- W2949671016 hasConcept C101738243 @default.
- W2949671016 hasConcept C104114177 @default.
- W2949671016 hasConcept C131979681 @default.
- W2949671016 hasConcept C134306372 @default.
- W2949671016 hasConcept C137800194 @default.
- W2949671016 hasConcept C153180895 @default.
- W2949671016 hasConcept C154945302 @default.
- W2949671016 hasConcept C167966045 @default.
- W2949671016 hasConcept C177148314 @default.
- W2949671016 hasConcept C17744445 @default.
- W2949671016 hasConcept C199539241 @default.
- W2949671016 hasConcept C2524010 @default.
- W2949671016 hasConcept C2776359362 @default.
- W2949671016 hasConcept C2776459999 @default.
- W2949671016 hasConcept C28719098 @default.
- W2949671016 hasConcept C33923547 @default.
- W2949671016 hasConcept C39890363 @default.
- W2949671016 hasConcept C41008148 @default.
- W2949671016 hasConcept C50644808 @default.
- W2949671016 hasConcept C59404180 @default.
- W2949671016 hasConcept C61224824 @default.
- W2949671016 hasConcept C76155785 @default.
- W2949671016 hasConcept C94625758 @default.
- W2949671016 hasConceptScore W2949671016C101738243 @default.
- W2949671016 hasConceptScore W2949671016C104114177 @default.
- W2949671016 hasConceptScore W2949671016C131979681 @default.
- W2949671016 hasConceptScore W2949671016C134306372 @default.
- W2949671016 hasConceptScore W2949671016C137800194 @default.
- W2949671016 hasConceptScore W2949671016C153180895 @default.
- W2949671016 hasConceptScore W2949671016C154945302 @default.
- W2949671016 hasConceptScore W2949671016C167966045 @default.
- W2949671016 hasConceptScore W2949671016C177148314 @default.
- W2949671016 hasConceptScore W2949671016C17744445 @default.
- W2949671016 hasConceptScore W2949671016C199539241 @default.
- W2949671016 hasConceptScore W2949671016C2524010 @default.
- W2949671016 hasConceptScore W2949671016C2776359362 @default.
- W2949671016 hasConceptScore W2949671016C2776459999 @default.
- W2949671016 hasConceptScore W2949671016C28719098 @default.
- W2949671016 hasConceptScore W2949671016C33923547 @default.
- W2949671016 hasConceptScore W2949671016C39890363 @default.