Matches in SemOpenAlex for { <https://semopenalex.org/work/W3114458132> ?p ?o ?g. }
- W3114458132 endingPage "35" @default.
- W3114458132 startingPage "19" @default.
- W3114458132 abstract "In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D shapes. Key to our construction is the introduction of a geometric distortion criterion, defined directly on the decoded shapes, translating the preservation of the metric on the decoding to the formation of linear paths in the underlying latent space. Our rationale lies in the observation that training samples alone are often insufficient to endow generative models with high fidelity, motivating the need for large training datasets. In contrast, metric preservation provides a rigorous way to control the amount of geometric distortion incurring in the construction of the latent space, leading in turn to synthetic samples of higher quality. We further demonstrate, for the first time, the adoption of differentiable intrinsic distances in the backpropagation of a geodesic loss. Our geometric priors are particularly relevant in the presence of scarce training data, where learning any meaningful latent structure can be especially challenging. The effectiveness and potential of our generative model is showcased in applications of style transfer, content generation, and shape completion." @default.
- W3114458132 created "2021-01-05" @default.
- W3114458132 creator A5030471485 @default.
- W3114458132 creator A5085428440 @default.
- W3114458132 creator A5087003679 @default.
- W3114458132 creator A5087051832 @default.
- W3114458132 creator A5091366774 @default.
- W3114458132 date "2020-01-01" @default.
- W3114458132 modified "2023-10-10" @default.
- W3114458132 title "LIMP: Learning Latent Shape Representations with Metric Preservation Priors" @default.
- W3114458132 cites W1979299495 @default.
- W3114458132 cites W1985907520 @default.
- W3114458132 cites W1998936196 @default.
- W3114458132 cites W1999690352 @default.
- W3114458132 cites W2015884050 @default.
- W3114458132 cites W2103975664 @default.
- W3114458132 cites W2154567221 @default.
- W3114458132 cites W2235901111 @default.
- W3114458132 cites W2277444324 @default.
- W3114458132 cites W2557166550 @default.
- W3114458132 cites W2566657318 @default.
- W3114458132 cites W2611752399 @default.
- W3114458132 cites W2728326942 @default.
- W3114458132 cites W2746892480 @default.
- W3114458132 cites W2791092480 @default.
- W3114458132 cites W2883221003 @default.
- W3114458132 cites W2883758202 @default.
- W3114458132 cites W2890370716 @default.
- W3114458132 cites W2905288042 @default.
- W3114458132 cites W2961368225 @default.
- W3114458132 cites W2962928839 @default.
- W3114458132 cites W2962934458 @default.
- W3114458132 cites W2963197375 @default.
- W3114458132 cites W2963242400 @default.
- W3114458132 cites W2963601843 @default.
- W3114458132 cites W2963627347 @default.
- W3114458132 cites W2963926543 @default.
- W3114458132 cites W2982687228 @default.
- W3114458132 cites W2984786182 @default.
- W3114458132 cites W2985683375 @default.
- W3114458132 cites W2989341556 @default.
- W3114458132 cites W2992956318 @default.
- W3114458132 cites W3003597184 @default.
- W3114458132 cites W3035163517 @default.
- W3114458132 cites W3102509876 @default.
- W3114458132 cites W3125178117 @default.
- W3114458132 cites W647235838 @default.
- W3114458132 doi "https://doi.org/10.1007/978-3-030-58580-8_2" @default.
- W3114458132 hasPublicationYear "2020" @default.
- W3114458132 type Work @default.
- W3114458132 sameAs 3114458132 @default.
- W3114458132 citedByCount "27" @default.
- W3114458132 countsByYear W31144581322020 @default.
- W3114458132 countsByYear W31144581322021 @default.
- W3114458132 countsByYear W31144581322022 @default.
- W3114458132 countsByYear W31144581322023 @default.
- W3114458132 crossrefType "book-chapter" @default.
- W3114458132 hasAuthorship W3114458132A5030471485 @default.
- W3114458132 hasAuthorship W3114458132A5085428440 @default.
- W3114458132 hasAuthorship W3114458132A5087003679 @default.
- W3114458132 hasAuthorship W3114458132A5087051832 @default.
- W3114458132 hasAuthorship W3114458132A5091366774 @default.
- W3114458132 hasBestOaLocation W31144581322 @default.
- W3114458132 hasConcept C107673813 @default.
- W3114458132 hasConcept C119857082 @default.
- W3114458132 hasConcept C126780896 @default.
- W3114458132 hasConcept C154945302 @default.
- W3114458132 hasConcept C162324750 @default.
- W3114458132 hasConcept C165818556 @default.
- W3114458132 hasConcept C167966045 @default.
- W3114458132 hasConcept C176217482 @default.
- W3114458132 hasConcept C177769412 @default.
- W3114458132 hasConcept C194257627 @default.
- W3114458132 hasConcept C21547014 @default.
- W3114458132 hasConcept C2524010 @default.
- W3114458132 hasConcept C2776257435 @default.
- W3114458132 hasConcept C2776459999 @default.
- W3114458132 hasConcept C31258907 @default.
- W3114458132 hasConcept C33923547 @default.
- W3114458132 hasConcept C39890363 @default.
- W3114458132 hasConcept C41008148 @default.
- W3114458132 hasConcept C51167844 @default.
- W3114458132 hasConcept C76155785 @default.
- W3114458132 hasConceptScore W3114458132C107673813 @default.
- W3114458132 hasConceptScore W3114458132C119857082 @default.
- W3114458132 hasConceptScore W3114458132C126780896 @default.
- W3114458132 hasConceptScore W3114458132C154945302 @default.
- W3114458132 hasConceptScore W3114458132C162324750 @default.
- W3114458132 hasConceptScore W3114458132C165818556 @default.
- W3114458132 hasConceptScore W3114458132C167966045 @default.
- W3114458132 hasConceptScore W3114458132C176217482 @default.
- W3114458132 hasConceptScore W3114458132C177769412 @default.
- W3114458132 hasConceptScore W3114458132C194257627 @default.
- W3114458132 hasConceptScore W3114458132C21547014 @default.
- W3114458132 hasConceptScore W3114458132C2524010 @default.
- W3114458132 hasConceptScore W3114458132C2776257435 @default.
- W3114458132 hasConceptScore W3114458132C2776459999 @default.
- W3114458132 hasConceptScore W3114458132C31258907 @default.