Building Accurate Physics-based Face Models from Data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10407992" target="_blank" >RIV/00216208:11320/19:10407992 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=P~ui_0xA1G" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=P~ui_0xA1G</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3340256" target="_blank" >10.1145/3340256</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Building Accurate Physics-based Face Models from Data

Popis výsledku v původním jazyce

The human face is an anatomical system exhibiting heterogenous and anisotropic mechanical behavior. This leads to complex deformations even in a neutral facial expression due to external forces such as gravity. We start by building a volumetric model from magnetic resonance images of a neutral facial expression. To obtain data on facial deformations we capture and register 3D scans of the face with different gravity directions and with various facial expressions. Our main contribution consists in solving an inverse physics problem where we learn mechanical properties of the face from our training data (3D scans). Specifically, we learn heterogenous stiffness and prestrain (which introduces anisotropy). The generalization capability of our resulting physics-based model is tested on 3D scans. We demonstrate that our model generates predictions of facial deformations more accurately than recent related physics-based techniques.

Název v anglickém jazyce

Building Accurate Physics-based Face Models from Data

Popis výsledku anglicky

The human face is an anatomical system exhibiting heterogenous and anisotropic mechanical behavior. This leads to complex deformations even in a neutral facial expression due to external forces such as gravity. We start by building a volumetric model from magnetic resonance images of a neutral facial expression. To obtain data on facial deformations we capture and register 3D scans of the face with different gravity directions and with various facial expressions. Our main contribution consists in solving an inverse physics problem where we learn mechanical properties of the face from our training data (3D scans). Specifically, we learn heterogenous stiffness and prestrain (which introduces anisotropy). The generalization capability of our resulting physics-based model is tested on 3D scans. We demonstrate that our model generates predictions of facial deformations more accurately than recent related physics-based techniques.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Proceedings of the ACM on Computer Graphics and Interactive Techniques

ISSN

2577-6193

e-ISSN

—

Svazek periodika

2019 / 2

Číslo periodika v rámci svazku

2019 / 7

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

16

Strana od-do

"nestrankovano"

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—