Geometric Modeling Explicit Implicit Representations Pdf View a pdf of the paper titled coupling explicit and implicit surface representations for generative 3d modeling, by omid poursaeed and matthew fisher and noam aigerman and vladimir g. kim. We propose a novel neural architecture for representing 3d surfaces, which harnesses two complementary shape representations: (i) an explicit representation via an atlas, i.e., embeddings of 2d domains into 3d; (ii) an implicit function representation, i.e., a scalar.
Coupling Explicit And Implicit Surface Representations For Generative Our framework enables a straightforward extraction of the surface from the explicit representation, as opposed to the more intricate marching cube like techniques required to extract a surface from the implicit function. We make these two representations synergistic by introducing novel consistency losses that ensure that the surface created from the atlas aligns with the level set of the implicit function. We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder, called im net, for shape generation, aimed at improving the visual quality of the generated shapes. We propose a novel neural architecture for representing 3d surfaces, which harnesses two complementary shape representations: (i) an explicit representation via an atlas (ii) an implicit function representation.
Pdf Coupling Explicit And Implicit Surface Representations For We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder, called im net, for shape generation, aimed at improving the visual quality of the generated shapes. We propose a novel neural architecture for representing 3d surfaces, which harnesses two complementary shape representations: (i) an explicit representation via an atlas (ii) an implicit function representation. The hybrid architecture combines explicit (atlasnet) and implicit (occupancynet) surface representations for superior 3d modeling. novel consistency losses align the outputs of atlasnet and occupancynet, enhancing surface quality and accuracy. Namely, my research lies at the intersection of geometry processing, deep learning, and optimization, with applications in 3d vision and computer graphics. Coupling explicit and implicit surface representations for generative 3d modeling.
Learning Implicit Fields For Generative Shape Modeling The hybrid architecture combines explicit (atlasnet) and implicit (occupancynet) surface representations for superior 3d modeling. novel consistency losses align the outputs of atlasnet and occupancynet, enhancing surface quality and accuracy. Namely, my research lies at the intersection of geometry processing, deep learning, and optimization, with applications in 3d vision and computer graphics. Coupling explicit and implicit surface representations for generative 3d modeling.
Learning Implicit Fields For Generative Shape Modeling Coupling explicit and implicit surface representations for generative 3d modeling.
Learning Implicit Fields For Generative Shape Modeling
Comments are closed.