FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3165220503> ?p ?o ?g. }

• W3165220503 endingPage "17" @default.
• W3165220503 startingPage "1" @default.
• W3165220503 abstract "3D shape generation is a fundamental operation in computer graphics. While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric details and complex structures, in a controllable manner. To tackle this, we introduce DSG-Net, a deep neural network that learns a disentangled structured & geometric mesh representation for 3D shapes, where two key aspects of shapes, geometry and structure, are encoded in a synergistic manner to ensure plausibility of the generated shapes, while also being disentangled as much as possible. This supports a range of novel shape generation applications with disentangled control, such as interpolation of structure (geometry) while keeping geometry (structure) unchanged. To achieve this, we simultaneously learn structure and geometry through variational autoencoders (VAEs) in a hierarchical manner for both, with bijective mappings at each level. In this manner, we effectively encode geometry and structure in separate latent spaces, while ensuring their compatibility: the structure is used to guide the geometry and vice versa. At the leaf level, the part geometry is represented using a conditional part VAE, to encode high-quality geometric details, guided by the structure context as the condition. Our method not only supports controllable generation applications, but also produces high-quality synthesized shapes, outperforming state-of-the-art methods." @default.
• W3165220503 created "2021-06-07" @default.
• W3165220503 creator A5014911195 @default.
• W3165220503 creator A5039573704 @default.
• W3165220503 creator A5051488351 @default.
• W3165220503 creator A5065368881 @default.
• W3165220503 creator A5072139431 @default.
• W3165220503 date "2022-08-12" @default.
• W3165220503 modified "2023-09-27" @default.
• W3165220503 title "DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation" @default.
• W3165220503 cites W1569512051 @default.
• W3165220503 cites W1644641054 @default.
• W3165220503 cites W1994838542 @default.
• W3165220503 cites W2031760064 @default.
• W3165220503 cites W2042997238 @default.
• W3165220503 cites W2092773680 @default.
• W3165220503 cites W2143668817 @default.
• W3165220503 cites W2342277278 @default.
• W3165220503 cites W2557269700 @default.
• W3165220503 cites W2558460151 @default.
• W3165220503 cites W2558748708 @default.
• W3165220503 cites W2560722161 @default.
• W3165220503 cites W2565662353 @default.
• W3165220503 cites W2603429625 @default.
• W3165220503 cites W2604249033 @default.
• W3165220503 cites W2612843093 @default.
• W3165220503 cites W2788158258 @default.
• W3165220503 cites W2796426482 @default.
• W3165220503 cites W2885163231 @default.
• W3165220503 cites W2887805175 @default.
• W3165220503 cites W2902035653 @default.
• W3165220503 cites W2936759181 @default.
• W3165220503 cites W2947464908 @default.
• W3165220503 cites W2961368225 @default.
• W3165220503 cites W2962770929 @default.
• W3165220503 cites W2962778872 @default.
• W3165220503 cites W2962780613 @default.
• W3165220503 cites W2962793481 @default.
• W3165220503 cites W2962849139 @default.
• W3165220503 cites W2963369474 @default.
• W3165220503 cites W2963400238 @default.
• W3165220503 cites W2963444790 @default.
• W3165220503 cites W2963627347 @default.
• W3165220503 cites W2963926543 @default.
• W3165220503 cites W2964118024 @default.
• W3165220503 cites W2964341242 @default.
• W3165220503 cites W2973965592 @default.
• W3165220503 cites W2985683375 @default.
• W3165220503 cites W2985840885 @default.
• W3165220503 cites W2986139246 @default.
• W3165220503 cites W2989341556 @default.
• W3165220503 cites W2992956318 @default.
• W3165220503 cites W2997180840 @default.
• W3165220503 cites W3004739592 @default.
• W3165220503 cites W3010196549 @default.
• W3165220503 cites W3034193465 @default.
• W3165220503 cites W3034917353 @default.
• W3165220503 cites W3035046407 @default.
• W3165220503 cites W3035163517 @default.
• W3165220503 cites W3035515538 @default.
• W3165220503 cites W3100124799 @default.
• W3165220503 cites W3100891210 @default.
• W3165220503 cites W3100955000 @default.
• W3165220503 cites W3108294306 @default.
• W3165220503 cites W3109125268 @default.
• W3165220503 cites W3128750067 @default.
• W3165220503 cites W3136891595 @default.
• W3165220503 cites W3169670866 @default.
• W3165220503 cites W3210542804 @default.
• W3165220503 cites W4250812768 @default.
• W3165220503 cites W4297598254 @default.
• W3165220503 doi "https://doi.org/10.1145/3526212" @default.
• W3165220503 hasPublicationYear "2022" @default.
• W3165220503 type Work @default.
• W3165220503 sameAs 3165220503 @default.
• W3165220503 citedByCount "4" @default.
• W3165220503 countsByYear W31652205032022 @default.
• W3165220503 countsByYear W31652205032023 @default.
• W3165220503 crossrefType "journal-article" @default.
• W3165220503 hasAuthorship W3165220503A5014911195 @default.
• W3165220503 hasAuthorship W3165220503A5039573704 @default.
• W3165220503 hasAuthorship W3165220503A5051488351 @default.
• W3165220503 hasAuthorship W3165220503A5065368881 @default.
• W3165220503 hasAuthorship W3165220503A5072139431 @default.
• W3165220503 hasBestOaLocation W31652205032 @default.
• W3165220503 hasConcept C104317684 @default.
• W3165220503 hasConcept C112604564 @default.
• W3165220503 hasConcept C114614502 @default.
• W3165220503 hasConcept C121684516 @default.
• W3165220503 hasConcept C154945302 @default.
• W3165220503 hasConcept C158843486 @default.
• W3165220503 hasConcept C17744445 @default.
• W3165220503 hasConcept C181095308 @default.
• W3165220503 hasConcept C184720557 @default.
• W3165220503 hasConcept C185592680 @default.
• W3165220503 hasConcept C199360897 @default.
• W3165220503 hasConcept C199539241 @default.
• W3165220503 hasConcept C2524010 @default.

• next