000267539 001__ 267539
000267539 005__ 20190918184512.0
000267539 037__ $$aSTUDENT
000267539 245__ $$aGeometric Deep Learning for Volumetric Computational Fluid Dynamics
000267539 260__ $$c2019-06-21
000267539 269__ $$a2019-06-21
000267539 300__ $$a67
000267539 336__ $$aStudent Projects
000267539 500__ $$aFor the slides, use pdfpc reader for visualizing correctly the videos.
000267539 520__ $$aThis master thesis explores ways to apply geometric deep learning to the field of numerical simulations with an emphasis on the Navier-Stokes equations. With the recent success of Deep Learning, there should be room for experimentation also in the field of fluid simulations. Here we lead such an experiment. We propose an end-to-end differentiable architecture that allow object-to-mesh predictions of fluid simulations. We provide a comparison with a baseline and visual results on three different datasets: airfoils, backward facing steps and winged drones.
000267539 542__ $$fCC BY
000267539 6531_ $$aGeometric Deep Learning
000267539 6531_ $$aConvolutional Neural Networks
000267539 6531_ $$aMultimodal Deep Learning
000267539 6531_ $$aComputational Fluid Dynamics
000267539 700__ $$aZampieri, Luca
000267539 720_2 $$g112366$$aFua, Pascal$$0240252
000267539 720_2 $$g244322$$aBaqué, Pierre Bruno$$0248469
000267539 720_2 $$g226056$$aDefferrard, Michaël$$0249515
000267539 720_2 $$g146262$$aFleuret, François$$0240254
000267539 720_2 $$g117182$$aFormaggia, Luca$$0241668
000267539 8560_ $$fluca.zampieri@epfl.ch
000267539 85641 $$yorchID$$uorcid.org/0000-0002-5369-0514
000267539 8564_ $$uhttps://infoscience.epfl.ch/record/267539/files/Master%20Thesis.pdf$$zPREPRINT$$s10592505
000267539 8564_ $$uhttps://infoscience.epfl.ch/record/267539/files/Poster.pdf$$zFinal$$s4107523
000267539 8564_ $$uhttps://infoscience.epfl.ch/record/267539/files/Slides.pdf$$zFinal$$s15771052
000267539 8564_ $$s10610936$$uhttps://infoscience.epfl.ch/record/267539/files/Thesis.pdf$$zFinal
000267539 909C0 $$zGrolimund, Raphael$$xU10659$$pCVLAB$$mpascal.fua@epfl.ch$$0252087
000267539 909CO $$pIC$$ooai:infoscience.epfl.ch:267539
000267539 960__ $$aluca.zampieri@epfl.ch
000267539 961__ $$apierre.devaud@epfl.ch
000267539 980__ $$aSTUDENT
000267539 980__ $$bMaster's Thesis 
000267539 981__ $$aoverwrite
000267539 999C0 $$zMarselli, Béatrice$$xU10380$$pLTS2$$mpierre.vandergheynst@epfl.ch$$0252392