Image-based Facial Rig Inversion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Tianxiang, Volino, Marco, Mustafa, Armin, Maguire, Greg, Kosk, Robert
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915556808982528
author Yang, Tianxiang
Volino, Marco
Mustafa, Armin
Maguire, Greg
Kosk, Robert
author_facet Yang, Tianxiang
Volino, Marco
Mustafa, Armin
Maguire, Greg
Kosk, Robert
contents We present an image-based rig inversion framework that leverages two modalities: RGB appearance and RGB-encoded normal maps. Each modality is processed by an independent Hiera transformer backbone, and the extracted features are fused to regress 102 rig parameters derived from the Facial Action Coding System (FACS). Experiments on synthetic and scanned datasets demonstrate that the method generalizes to scanned data, producing faithful reconstructions.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13933
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Image-based Facial Rig Inversion
Yang, Tianxiang
Volino, Marco
Mustafa, Armin
Maguire, Greg
Kosk, Robert
Image and Video Processing
68T45 (Primary) 68T07, 68U05 (Secondary)
I.3.7; I.2.10; I.4.8
We present an image-based rig inversion framework that leverages two modalities: RGB appearance and RGB-encoded normal maps. Each modality is processed by an independent Hiera transformer backbone, and the extracted features are fused to regress 102 rig parameters derived from the Facial Action Coding System (FACS). Experiments on synthetic and scanned datasets demonstrate that the method generalizes to scanned data, producing faithful reconstructions.
title Image-based Facial Rig Inversion
topic Image and Video Processing
68T45 (Primary) 68T07, 68U05 (Secondary)
I.3.7; I.2.10; I.4.8
url https://arxiv.org/abs/2510.13933