Examinando por Autor "Theobalt, Christian"
Mostrando 1 - 1 de 1
- Resultados por página
- Opciones de ordenación
Ítem Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera(ACM Transactions on Graphics, 2019) Mueller, Franziska; Davis, Micah; Bernard, Florian; Sotnychenko, Oleksandr; Verschoor, Mickeal; Otaduy, Miguel A.; Casas, Dan; Theobalt, ChristianWepresentanovelmethodforreal-timeposeandshapereconstructionof twostronglyinteractinghands.Ourapproachisthefirsttwo-handtracking solutionthatcombinesanextensivelistoffavorableproperties,namelyitis marker-less,usesasingleconsumer-leveldepthcamera,runsinrealtime, handlesinter-andintra-handcollisions,andautomaticallyadjuststothe user’shandshape.Inordertoachievethis,weembedarecentparametric handposeandshapemodelandadensecorrespondencepredictorbasedon adeepneuralnetworkintoasuitableenergyminimizationframework.For trainingthecorrespondencepredictionnetwork,wesynthesizeatwo-hand dataset based on physical simulations that includes both hand pose and shapeannotationswhileatthesametimeavoidinginter-handpenetrations. Toachievereal-timerates,wephrasethemodelfittingintermsofanonlinear least-squaresproblemsothattheenergycanbeoptimizedbasedonahighly efficient GPU-based Gauss-Newton optimizer. We show state-of-the-art resultsinscenesthatexceedthecomplexityleveldemonstratedbyprevious