Matches in SemOpenAlex for { <https://semopenalex.org/work/W2925564436> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2925564436 endingPage "76" @default.
- W2925564436 startingPage "63" @default.
- W2925564436 abstract "Deep learning techniques for geometric processing have been gaining popularity in recent years, various deep models (i.e., deep learning methods based on neural networks) are developed with enhanced performance and functionality in conventional geometric tasks such as shape classification, segmentation, and recognition. Yet, deep models would rely on large datasets for the training and testing purpose, which are generally lacking as 3D shape geometry could not be easily acquired and/or reconstructed. In this paper, we propose a new 3D shape dataset augmentation method by learning the deformation between shapes in a highly reduced latent space while affording interactive control of shape generation. Specifically, we model each shape using a concise skeleton-based representation, and then we apply Gaussian Process Latent Variable Model (GPLVM) to embed all shape skeletons into a low-dimensional latent space, where new skeletons could be generated with diverse kinds of flexible control and/or quantitative guidance. A second network that learns the displacement between shapes can be employed to produce new 3D shape from newly-generated skeletons. Compared with popular computer vision techniques, our new generative method could overcome remaining challenges of 3D shape augmentation with new characteristics. Specifically, our new method is capable of transforming 3D shapes in a more liberal way, preserving their geometric properties at a semantic level, and creating new shape with ease and flexible control. Extensive experiments have exhibited the capability and flexibility of our new method in generating new shapes using only few samples. Our shape augmentation is an effective way to simultaneously improve the shape creation capability and the shape extrapolation accuracy, and it is also of immediate benefit to almost all deep learning tasks in geometric modeling and processing." @default.
- W2925564436 created "2019-04-11" @default.
- W2925564436 creator A5007658088 @default.
- W2925564436 creator A5035153076 @default.
- W2925564436 creator A5063211322 @default.
- W2925564436 creator A5065912071 @default.
- W2925564436 creator A5074985694 @default.
- W2925564436 date "2019-05-01" @default.
- W2925564436 modified "2023-10-16" @default.
- W2925564436 title "Quantitative and flexible 3D shape dataset augmentation via latent space embedding and deformation learning" @default.
- W2925564436 cites W1702995668 @default.
- W2925564436 cites W1827769268 @default.
- W2925564436 cites W2000391612 @default.
- W2925564436 cites W2004167999 @default.
- W2925564436 cites W2021285100 @default.
- W2925564436 cites W2069728322 @default.
- W2925564436 cites W2143668817 @default.
- W2925564436 cites W2402720675 @default.
- W2925564436 cites W2612843093 @default.
- W2925564436 cites W2919115771 @default.
- W2925564436 cites W3004726950 @default.
- W2925564436 cites W3104503957 @default.
- W2925564436 cites W4251002338 @default.
- W2925564436 doi "https://doi.org/10.1016/j.cagd.2019.04.017" @default.
- W2925564436 hasPublicationYear "2019" @default.
- W2925564436 type Work @default.
- W2925564436 sameAs 2925564436 @default.
- W2925564436 citedByCount "2" @default.
- W2925564436 countsByYear W29255644362023 @default.
- W2925564436 crossrefType "journal-article" @default.
- W2925564436 hasAuthorship W2925564436A5007658088 @default.
- W2925564436 hasAuthorship W2925564436A5035153076 @default.
- W2925564436 hasAuthorship W2925564436A5063211322 @default.
- W2925564436 hasAuthorship W2925564436A5065912071 @default.
- W2925564436 hasAuthorship W2925564436A5074985694 @default.
- W2925564436 hasBestOaLocation W29255644361 @default.
- W2925564436 hasConcept C108583219 @default.
- W2925564436 hasConcept C112604564 @default.
- W2925564436 hasConcept C112785775 @default.
- W2925564436 hasConcept C119857082 @default.
- W2925564436 hasConcept C129641003 @default.
- W2925564436 hasConcept C153180895 @default.
- W2925564436 hasConcept C154945302 @default.
- W2925564436 hasConcept C17744445 @default.
- W2925564436 hasConcept C199360897 @default.
- W2925564436 hasConcept C199539241 @default.
- W2925564436 hasConcept C2776359362 @default.
- W2925564436 hasConcept C31972630 @default.
- W2925564436 hasConcept C41008148 @default.
- W2925564436 hasConcept C41608201 @default.
- W2925564436 hasConcept C50644808 @default.
- W2925564436 hasConcept C89600930 @default.
- W2925564436 hasConcept C94625758 @default.
- W2925564436 hasConcept C97686452 @default.
- W2925564436 hasConceptScore W2925564436C108583219 @default.
- W2925564436 hasConceptScore W2925564436C112604564 @default.
- W2925564436 hasConceptScore W2925564436C112785775 @default.
- W2925564436 hasConceptScore W2925564436C119857082 @default.
- W2925564436 hasConceptScore W2925564436C129641003 @default.
- W2925564436 hasConceptScore W2925564436C153180895 @default.
- W2925564436 hasConceptScore W2925564436C154945302 @default.
- W2925564436 hasConceptScore W2925564436C17744445 @default.
- W2925564436 hasConceptScore W2925564436C199360897 @default.
- W2925564436 hasConceptScore W2925564436C199539241 @default.
- W2925564436 hasConceptScore W2925564436C2776359362 @default.
- W2925564436 hasConceptScore W2925564436C31972630 @default.
- W2925564436 hasConceptScore W2925564436C41008148 @default.
- W2925564436 hasConceptScore W2925564436C41608201 @default.
- W2925564436 hasConceptScore W2925564436C50644808 @default.
- W2925564436 hasConceptScore W2925564436C89600930 @default.
- W2925564436 hasConceptScore W2925564436C94625758 @default.
- W2925564436 hasConceptScore W2925564436C97686452 @default.
- W2925564436 hasFunder F4320306076 @default.
- W2925564436 hasFunder F4320321001 @default.
- W2925564436 hasLocation W29255644361 @default.
- W2925564436 hasOpenAccess W2925564436 @default.
- W2925564436 hasPrimaryLocation W29255644361 @default.
- W2925564436 hasRelatedWork W1998358089 @default.
- W2925564436 hasRelatedWork W2008311803 @default.
- W2925564436 hasRelatedWork W2070688477 @default.
- W2925564436 hasRelatedWork W2095298292 @default.
- W2925564436 hasRelatedWork W2149185563 @default.
- W2925564436 hasRelatedWork W2502757031 @default.
- W2925564436 hasRelatedWork W2941291816 @default.
- W2925564436 hasRelatedWork W3143950454 @default.
- W2925564436 hasRelatedWork W4248609557 @default.
- W2925564436 hasRelatedWork W4255540734 @default.
- W2925564436 hasVolume "71" @default.
- W2925564436 isParatext "false" @default.
- W2925564436 isRetracted "false" @default.
- W2925564436 magId "2925564436" @default.
- W2925564436 workType "article" @default.