Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226407019> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4226407019 abstract "We introduce PhysXNet, a learning-based approach to predict the dynamics of deformable clothes given 3D skeleton motion sequences of humans wearing these clothes. The proposed model is adaptable to a large variety of garments and changing topologies, without need of being retrained. Such simulations are typically carried out by physics engines that require manual human expertise and are subjectto computationally intensive computations. PhysXNet, by contrast, is a fully differentiable deep network that at inference is able to estimate the geometry of dense cloth meshes in a matter of milliseconds, and thus, can be readily deployed as a layer of a larger deep learning architecture. This efficiency is achieved thanks to the specific parameterization of the clothes we consider, based on 3D UV maps encoding spatial garment displacements. The problem is then formulated as a mapping between the human kinematics space (represented also by 3D UV maps of the undressed body mesh) into the clothes displacement UV maps, which we learn using a conditional GAN with a discriminator that enforces feasible deformations. We train simultaneously our model for three garment templates, tops, bottoms and dresses for which we simulate deformations under 50 different human actions. Nevertheless, the UV map representation we consider allows encapsulating many different cloth topologies, and at test we can simulate garments even if we did not specifically train for them. A thorough evaluation demonstrates that PhysXNet delivers cloth deformations very close to those computed with the physical engine, opening the door to be effectively integrated within deeplearning pipelines." @default.
- W4226407019 created "2022-05-05" @default.
- W4226407019 creator A5023922146 @default.
- W4226407019 creator A5039307249 @default.
- W4226407019 creator A5063541182 @default.
- W4226407019 date "2021-11-13" @default.
- W4226407019 modified "2023-09-23" @default.
- W4226407019 title "PhysXNet: A Customizable Approach for LearningCloth Dynamics on Dressed People" @default.
- W4226407019 hasPublicationYear "2021" @default.
- W4226407019 type Work @default.
- W4226407019 citedByCount "0" @default.
- W4226407019 crossrefType "posted-content" @default.
- W4226407019 hasAuthorship W4226407019A5023922146 @default.
- W4226407019 hasAuthorship W4226407019A5039307249 @default.
- W4226407019 hasAuthorship W4226407019A5063541182 @default.
- W4226407019 hasBestOaLocation W42264070191 @default.
- W4226407019 hasConcept C108583219 @default.
- W4226407019 hasConcept C111919701 @default.
- W4226407019 hasConcept C11413529 @default.
- W4226407019 hasConcept C119599485 @default.
- W4226407019 hasConcept C121332964 @default.
- W4226407019 hasConcept C121684516 @default.
- W4226407019 hasConcept C127413603 @default.
- W4226407019 hasConcept C134306372 @default.
- W4226407019 hasConcept C154945302 @default.
- W4226407019 hasConcept C17744445 @default.
- W4226407019 hasConcept C184720557 @default.
- W4226407019 hasConcept C199539241 @default.
- W4226407019 hasConcept C199845137 @default.
- W4226407019 hasConcept C202615002 @default.
- W4226407019 hasConcept C2776359362 @default.
- W4226407019 hasConcept C31487907 @default.
- W4226407019 hasConcept C31972630 @default.
- W4226407019 hasConcept C33923547 @default.
- W4226407019 hasConcept C39920418 @default.
- W4226407019 hasConcept C41008148 @default.
- W4226407019 hasConcept C45374587 @default.
- W4226407019 hasConcept C50637493 @default.
- W4226407019 hasConcept C74650414 @default.
- W4226407019 hasConcept C94625758 @default.
- W4226407019 hasConceptScore W4226407019C108583219 @default.
- W4226407019 hasConceptScore W4226407019C111919701 @default.
- W4226407019 hasConceptScore W4226407019C11413529 @default.
- W4226407019 hasConceptScore W4226407019C119599485 @default.
- W4226407019 hasConceptScore W4226407019C121332964 @default.
- W4226407019 hasConceptScore W4226407019C121684516 @default.
- W4226407019 hasConceptScore W4226407019C127413603 @default.
- W4226407019 hasConceptScore W4226407019C134306372 @default.
- W4226407019 hasConceptScore W4226407019C154945302 @default.
- W4226407019 hasConceptScore W4226407019C17744445 @default.
- W4226407019 hasConceptScore W4226407019C184720557 @default.
- W4226407019 hasConceptScore W4226407019C199539241 @default.
- W4226407019 hasConceptScore W4226407019C199845137 @default.
- W4226407019 hasConceptScore W4226407019C202615002 @default.
- W4226407019 hasConceptScore W4226407019C2776359362 @default.
- W4226407019 hasConceptScore W4226407019C31487907 @default.
- W4226407019 hasConceptScore W4226407019C31972630 @default.
- W4226407019 hasConceptScore W4226407019C33923547 @default.
- W4226407019 hasConceptScore W4226407019C39920418 @default.
- W4226407019 hasConceptScore W4226407019C41008148 @default.
- W4226407019 hasConceptScore W4226407019C45374587 @default.
- W4226407019 hasConceptScore W4226407019C50637493 @default.
- W4226407019 hasConceptScore W4226407019C74650414 @default.
- W4226407019 hasConceptScore W4226407019C94625758 @default.
- W4226407019 hasLocation W42264070191 @default.
- W4226407019 hasLocation W42264070192 @default.
- W4226407019 hasOpenAccess W4226407019 @default.
- W4226407019 hasPrimaryLocation W42264070191 @default.
- W4226407019 hasRelatedWork W1055231 @default.
- W4226407019 hasRelatedWork W11437179 @default.
- W4226407019 hasRelatedWork W13086417 @default.
- W4226407019 hasRelatedWork W13571693 @default.
- W4226407019 hasRelatedWork W1393322 @default.
- W4226407019 hasRelatedWork W18063311 @default.
- W4226407019 hasRelatedWork W4917522 @default.
- W4226407019 hasRelatedWork W6451020 @default.
- W4226407019 hasRelatedWork W795352 @default.
- W4226407019 hasRelatedWork W8488391 @default.
- W4226407019 isParatext "false" @default.
- W4226407019 isRetracted "false" @default.
- W4226407019 workType "article" @default.