Near-realtime Facial Animation by Deep 3D Simulation Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Hyojoon, Srinivasan, Sangeetha Grama, Cong, Matthew, Kim, Doyub, Kim, Byungsoo, Swartz, Jonathan, Museth, Ken, Sifakis, Eftychios
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912033881980928
author Park, Hyojoon
Srinivasan, Sangeetha Grama
Cong, Matthew
Kim, Doyub
Kim, Byungsoo
Swartz, Jonathan
Museth, Ken
Sifakis, Eftychios
author_facet Park, Hyojoon
Srinivasan, Sangeetha Grama
Cong, Matthew
Kim, Doyub
Kim, Byungsoo
Swartz, Jonathan
Museth, Ken
Sifakis, Eftychios
contents We present a neural network-based simulation super-resolution framework that can efficiently and realistically enhance a facial performance produced by a low-cost, realtime physics-based simulation to a level of detail that closely approximates that of a reference-quality off-line simulator with much higher resolution (26x element count in our examples) and accurate physical modeling. Our approach is rooted in our ability to construct - via simulation - a training set of paired frames, from the low- and high-resolution simulators respectively, that are in semantic correspondence with each other. We use face animation as an exemplar of such a simulation domain, where creating this semantic congruence is achieved by simply dialing in the same muscle actuation controls and skeletal pose in the two simulators. Our proposed neural network super-resolution framework generalizes from this training set to unseen expressions, compensates for modeling discrepancies between the two simulations due to limited resolution or cost-cutting approximations in the real-time variant, and does not require any semantic descriptors or parameters to be provided as input, other than the result of the real-time simulation. We evaluate the efficacy of our pipeline on a variety of expressive performances and provide comparisons and ablation experiments for plausible variations and alternatives to our proposed scheme.
format Preprint
id arxiv_https___arxiv_org_abs_2305_03216
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Near-realtime Facial Animation by Deep 3D Simulation Super-Resolution
Park, Hyojoon
Srinivasan, Sangeetha Grama
Cong, Matthew
Kim, Doyub
Kim, Byungsoo
Swartz, Jonathan
Museth, Ken
Sifakis, Eftychios
Graphics
Artificial Intelligence
We present a neural network-based simulation super-resolution framework that can efficiently and realistically enhance a facial performance produced by a low-cost, realtime physics-based simulation to a level of detail that closely approximates that of a reference-quality off-line simulator with much higher resolution (26x element count in our examples) and accurate physical modeling. Our approach is rooted in our ability to construct - via simulation - a training set of paired frames, from the low- and high-resolution simulators respectively, that are in semantic correspondence with each other. We use face animation as an exemplar of such a simulation domain, where creating this semantic congruence is achieved by simply dialing in the same muscle actuation controls and skeletal pose in the two simulators. Our proposed neural network super-resolution framework generalizes from this training set to unseen expressions, compensates for modeling discrepancies between the two simulations due to limited resolution or cost-cutting approximations in the real-time variant, and does not require any semantic descriptors or parameters to be provided as input, other than the result of the real-time simulation. We evaluate the efficacy of our pipeline on a variety of expressive performances and provide comparisons and ablation experiments for plausible variations and alternatives to our proposed scheme.
title Near-realtime Facial Animation by Deep 3D Simulation Super-Resolution
topic Graphics
Artificial Intelligence
url https://arxiv.org/abs/2305.03216