Implicit Neural Representation for Physics-driven Actuated Soft Bodies

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Lingchen, Kim, Byungsoo, Zoss, Gaspard, Gözcü, Baran, Gross, Markus, Solenthaler, Barbara
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911765275607040
author Yang, Lingchen
Kim, Byungsoo
Zoss, Gaspard
Gözcü, Baran
Gross, Markus
Solenthaler, Barbara
author_facet Yang, Lingchen
Kim, Byungsoo
Zoss, Gaspard
Gözcü, Baran
Gross, Markus
Solenthaler, Barbara
contents Active soft bodies can affect their shape through an internal actuation mechanism that induces a deformation. Similar to recent work, this paper utilizes a differentiable, quasi-static, and physics-based simulation layer to optimize for actuation signals parameterized by neural networks. Our key contribution is a general and implicit formulation to control active soft bodies by defining a function that enables a continuous mapping from a spatial point in the material space to the actuation value. This property allows us to capture the signal's dominant frequencies, making the method discretization agnostic and widely applicable. We extend our implicit model to mandible kinematics for the particular case of facial animation and show that we can reliably reproduce facial expressions captured with high-quality capture systems. We apply the method to volumetric soft bodies, human poses, and facial expressions, demonstrating artist-friendly properties, such as simple control over the latent space and resolution invariance at test time.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14861
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Implicit Neural Representation for Physics-driven Actuated Soft Bodies
Yang, Lingchen
Kim, Byungsoo
Zoss, Gaspard
Gözcü, Baran
Gross, Markus
Solenthaler, Barbara
Computer Vision and Pattern Recognition
Graphics
Active soft bodies can affect their shape through an internal actuation mechanism that induces a deformation. Similar to recent work, this paper utilizes a differentiable, quasi-static, and physics-based simulation layer to optimize for actuation signals parameterized by neural networks. Our key contribution is a general and implicit formulation to control active soft bodies by defining a function that enables a continuous mapping from a spatial point in the material space to the actuation value. This property allows us to capture the signal's dominant frequencies, making the method discretization agnostic and widely applicable. We extend our implicit model to mandible kinematics for the particular case of facial animation and show that we can reliably reproduce facial expressions captured with high-quality capture systems. We apply the method to volumetric soft bodies, human poses, and facial expressions, demonstrating artist-friendly properties, such as simple control over the latent space and resolution invariance at test time.
title Implicit Neural Representation for Physics-driven Actuated Soft Bodies
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2401.14861