FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035668851> ?p ?o ?g. }

• W3035668851 abstract "In this paper, we present TailorNet, a neural model which predicts clothing deformation in 3D as a function of three factors: pose, shape and style (garment geometry), while retaining wrinkle detail. This goes beyond prior models, which are either specific to one style and shape, or generalize to different shapes producing smooth results, despite being style specific. Our hypothesis is that (even non-linear) combinations of examples smoothes out high frequency components such as fine-wrinkles, which makes learning the three factors jointly hard. At the heart of our technique is a decomposition of deformation into a high frequency and a low frequency component. While the low-frequency component is predicted from pose, shape and style parameters with an MLP, the high-frequency component is predicted with a mixture of shape-style specific pose models. The weights of the mixture are computed with a narrow bandwidth kernel to guarantee that only predictions with similar high-frequency patterns are combined. The style variation is obtained by computing, in a canonical pose, a subspace of deformation, which satisfies physical constraints such as inter-penetration, and draping on the body. TailorNet delivers 3D garments which retain the wrinkles from the physics based simulations (PBS) it is learned from, while running more than 1000 times faster. In contrast to classical PBS, TailorNet is easy to use and fully differentiable, which is crucial for computer vision and learning algorithms. Several experiments demonstrate TailorNet produces more realistic results than prior work, and even generates temporally coherent deformations on sequences of the AMASS dataset, despite being trained on static poses from a different dataset. To stimulate further research in this direction, we will make a dataset consisting of 55800 frames, as well as our model publicly available at https://virtualhumans.mpi-inf.mpg.de/tailornet/." @default.
• W3035668851 created "2020-06-19" @default.
• W3035668851 creator A5062569341 @default.
• W3035668851 creator A5076908763 @default.
• W3035668851 creator A5085976775 @default.
• W3035668851 date "2020-06-01" @default.
• W3035668851 modified "2023-10-02" @default.
• W3035668851 title "TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style" @default.
• W3035668851 cites W1798731418 @default.
• W3035668851 cites W1834323716 @default.
• W3035668851 cites W1967494143 @default.
• W3035668851 cites W1985351089 @default.
• W3035668851 cites W1986724888 @default.
• W3035668851 cites W2000214666 @default.
• W3035668851 cites W2008537322 @default.
• W3035668851 cites W2023883335 @default.
• W3035668851 cites W2071663264 @default.
• W3035668851 cites W2071839134 @default.
• W3035668851 cites W2132836675 @default.
• W3035668851 cites W2160547390 @default.
• W3035668851 cites W2169417172 @default.
• W3035668851 cites W2739405427 @default.
• W3035668851 cites W2793768642 @default.
• W3035668851 cites W2798777978 @default.
• W3035668851 cites W2810283892 @default.
• W3035668851 cites W2894878561 @default.
• W3035668851 cites W2920928264 @default.
• W3035668851 cites W2921745007 @default.
• W3035668851 cites W2946584893 @default.
• W3035668851 cites W2962831356 @default.
• W3035668851 cites W2963097270 @default.
• W3035668851 cites W2963197375 @default.
• W3035668851 cites W2963335855 @default.
• W3035668851 cites W2963515833 @default.
• W3035668851 cites W2963630103 @default.
• W3035668851 cites W2963907666 @default.
• W3035668851 cites W2964050021 @default.
• W3035668851 cites W2964318046 @default.
• W3035668851 cites W2971467054 @default.
• W3035668851 cites W2979283733 @default.
• W3035668851 cites W2981950698 @default.
• W3035668851 cites W2984983779 @default.
• W3035668851 cites W2990737297 @default.
• W3035668851 cites W3006964082 @default.
• W3035668851 cites W3035520874 @default.
• W3035668851 cites W3137381876 @default.
• W3035668851 cites W4238731981 @default.
• W3035668851 cites W4250595268 @default.
• W3035668851 doi "https://doi.org/10.1109/cvpr42600.2020.00739" @default.
• W3035668851 hasPublicationYear "2020" @default.
• W3035668851 type Work @default.
• W3035668851 sameAs 3035668851 @default.
• W3035668851 citedByCount "152" @default.
• W3035668851 countsByYear W30356688512019 @default.
• W3035668851 countsByYear W30356688512020 @default.
• W3035668851 countsByYear W30356688512021 @default.
• W3035668851 countsByYear W30356688512022 @default.
• W3035668851 countsByYear W30356688512023 @default.
• W3035668851 crossrefType "proceedings-article" @default.
• W3035668851 hasAuthorship W3035668851A5062569341 @default.
• W3035668851 hasAuthorship W3035668851A5076908763 @default.
• W3035668851 hasAuthorship W3035668851A5085976775 @default.
• W3035668851 hasBestOaLocation W30356688512 @default.
• W3035668851 hasConcept C121332964 @default.
• W3035668851 hasConcept C14036430 @default.
• W3035668851 hasConcept C154945302 @default.
• W3035668851 hasConcept C159985019 @default.
• W3035668851 hasConcept C166957645 @default.
• W3035668851 hasConcept C168167062 @default.
• W3035668851 hasConcept C192562407 @default.
• W3035668851 hasConcept C2777872592 @default.
• W3035668851 hasConcept C31972630 @default.
• W3035668851 hasConcept C41008148 @default.
• W3035668851 hasConcept C530175646 @default.
• W3035668851 hasConcept C78458016 @default.
• W3035668851 hasConcept C86803240 @default.
• W3035668851 hasConcept C95457728 @default.
• W3035668851 hasConcept C97355855 @default.
• W3035668851 hasConceptScore W3035668851C121332964 @default.
• W3035668851 hasConceptScore W3035668851C14036430 @default.
• W3035668851 hasConceptScore W3035668851C154945302 @default.
• W3035668851 hasConceptScore W3035668851C159985019 @default.
• W3035668851 hasConceptScore W3035668851C166957645 @default.
• W3035668851 hasConceptScore W3035668851C168167062 @default.
• W3035668851 hasConceptScore W3035668851C192562407 @default.
• W3035668851 hasConceptScore W3035668851C2777872592 @default.
• W3035668851 hasConceptScore W3035668851C31972630 @default.
• W3035668851 hasConceptScore W3035668851C41008148 @default.
• W3035668851 hasConceptScore W3035668851C530175646 @default.
• W3035668851 hasConceptScore W3035668851C78458016 @default.
• W3035668851 hasConceptScore W3035668851C86803240 @default.
• W3035668851 hasConceptScore W3035668851C95457728 @default.
• W3035668851 hasConceptScore W3035668851C97355855 @default.
• W3035668851 hasLocation W30356688511 @default.
• W3035668851 hasLocation W30356688512 @default.
• W3035668851 hasOpenAccess W3035668851 @default.
• W3035668851 hasPrimaryLocation W30356688511 @default.
• W3035668851 hasRelatedWork W11888129 @default.
• W3035668851 hasRelatedWork W12133522 @default.
• W3035668851 hasRelatedWork W13187899 @default.

• next