Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312700461> ?p ?o ?g. }
- W4312700461 endingPage "502" @default.
- W4312700461 startingPage "485" @default.
- W4312700461 abstract "In recent years, neural implicit representations have made remarkable progress in modeling of 3D shapes with arbitrary topology. In this work, we address two key limitations of such representations, in failing to capture local 3D geometric fine details, and to learn from and generalize to shapes with unseen 3D transformations. To this end, we introduce a novel family of graph implicit functions with equivariant layers that facilitates modeling fine local details and guaranteed robustness to various groups of geometric transformations, through local k-NN graph embeddings with sparse point set observations at multiple resolutions. Our method improves over the existing rotation-equivariant implicit function from 0.69 to 0.89 (IoU) on the ShapeNet reconstruction task. We also show that our equivariant implicit function can be extended to other types of similarity transformations and generalizes to unseen translations and scaling." @default.
- W4312700461 created "2023-01-05" @default.
- W4312700461 creator A5002625178 @default.
- W4312700461 creator A5053359186 @default.
- W4312700461 creator A5056977175 @default.
- W4312700461 creator A5088583491 @default.
- W4312700461 creator A5090467618 @default.
- W4312700461 date "2022-01-01" @default.
- W4312700461 modified "2023-09-30" @default.
- W4312700461 title "3D Equivariant Graph Implicit Functions" @default.
- W4312700461 cites W1901129140 @default.
- W4312700461 cites W2576915720 @default.
- W4312700461 cites W2594519801 @default.
- W4312700461 cites W2769152880 @default.
- W4312700461 cites W2891396148 @default.
- W4312700461 cites W2962849139 @default.
- W4312700461 cites W2963627347 @default.
- W4312700461 cites W2963719584 @default.
- W4312700461 cites W2963926543 @default.
- W4312700461 cites W2979750740 @default.
- W4312700461 cites W2981978060 @default.
- W4312700461 cites W3034317823 @default.
- W4312700461 cites W3034395814 @default.
- W4312700461 cites W3034964128 @default.
- W4312700461 cites W3034968345 @default.
- W4312700461 cites W3035507572 @default.
- W4312700461 cites W3035515538 @default.
- W4312700461 cites W3035591705 @default.
- W4312700461 cites W3095473874 @default.
- W4312700461 cites W3095682719 @default.
- W4312700461 cites W3106569148 @default.
- W4312700461 cites W3106739598 @default.
- W4312700461 cites W3117476483 @default.
- W4312700461 cites W3118448400 @default.
- W4312700461 cites W3158545781 @default.
- W4312700461 cites W3184957317 @default.
- W4312700461 cites W4229035826 @default.
- W4312700461 cites W4283215246 @default.
- W4312700461 cites W4285102336 @default.
- W4312700461 doi "https://doi.org/10.1007/978-3-031-20062-5_28" @default.
- W4312700461 hasPublicationYear "2022" @default.
- W4312700461 type Work @default.
- W4312700461 citedByCount "2" @default.
- W4312700461 countsByYear W43127004612023 @default.
- W4312700461 crossrefType "book-chapter" @default.
- W4312700461 hasAuthorship W4312700461A5002625178 @default.
- W4312700461 hasAuthorship W4312700461A5053359186 @default.
- W4312700461 hasAuthorship W4312700461A5056977175 @default.
- W4312700461 hasAuthorship W4312700461A5088583491 @default.
- W4312700461 hasAuthorship W4312700461A5090467618 @default.
- W4312700461 hasBestOaLocation W43127004612 @default.
- W4312700461 hasConcept C104317684 @default.
- W4312700461 hasConcept C11413529 @default.
- W4312700461 hasConcept C114614502 @default.
- W4312700461 hasConcept C132525143 @default.
- W4312700461 hasConcept C154945302 @default.
- W4312700461 hasConcept C171036898 @default.
- W4312700461 hasConcept C184720557 @default.
- W4312700461 hasConcept C185592680 @default.
- W4312700461 hasConcept C202444582 @default.
- W4312700461 hasConcept C2524010 @default.
- W4312700461 hasConcept C33923547 @default.
- W4312700461 hasConcept C41008148 @default.
- W4312700461 hasConcept C55493867 @default.
- W4312700461 hasConcept C63479239 @default.
- W4312700461 hasConcept C80444323 @default.
- W4312700461 hasConcept C99844830 @default.
- W4312700461 hasConceptScore W4312700461C104317684 @default.
- W4312700461 hasConceptScore W4312700461C11413529 @default.
- W4312700461 hasConceptScore W4312700461C114614502 @default.
- W4312700461 hasConceptScore W4312700461C132525143 @default.
- W4312700461 hasConceptScore W4312700461C154945302 @default.
- W4312700461 hasConceptScore W4312700461C171036898 @default.
- W4312700461 hasConceptScore W4312700461C184720557 @default.
- W4312700461 hasConceptScore W4312700461C185592680 @default.
- W4312700461 hasConceptScore W4312700461C202444582 @default.
- W4312700461 hasConceptScore W4312700461C2524010 @default.
- W4312700461 hasConceptScore W4312700461C33923547 @default.
- W4312700461 hasConceptScore W4312700461C41008148 @default.
- W4312700461 hasConceptScore W4312700461C55493867 @default.
- W4312700461 hasConceptScore W4312700461C63479239 @default.
- W4312700461 hasConceptScore W4312700461C80444323 @default.
- W4312700461 hasConceptScore W4312700461C99844830 @default.
- W4312700461 hasLocation W43127004611 @default.
- W4312700461 hasLocation W43127004612 @default.
- W4312700461 hasLocation W43127004613 @default.
- W4312700461 hasLocation W43127004614 @default.
- W4312700461 hasOpenAccess W4312700461 @default.
- W4312700461 hasPrimaryLocation W43127004611 @default.
- W4312700461 hasRelatedWork W2011881105 @default.
- W4312700461 hasRelatedWork W2035976912 @default.
- W4312700461 hasRelatedWork W2541791370 @default.
- W4312700461 hasRelatedWork W2775182575 @default.
- W4312700461 hasRelatedWork W3094187672 @default.
- W4312700461 hasRelatedWork W3164116745 @default.
- W4312700461 hasRelatedWork W3213778687 @default.
- W4312700461 hasRelatedWork W4311616284 @default.
- W4312700461 hasRelatedWork W4384027078 @default.