SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargeting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Josi, Arthur, Hafemann, Luiz Gustavo, Dib, Abdallah, Got, Emeline, Cruz, Rafael M. O., Carbonneau, Marc-Andre
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915383653433344
author Josi, Arthur
Hafemann, Luiz Gustavo
Dib, Abdallah
Got, Emeline
Cruz, Rafael M. O.
Carbonneau, Marc-Andre
author_facet Josi, Arthur
Hafemann, Luiz Gustavo
Dib, Abdallah
Got, Emeline
Cruz, Rafael M. O.
Carbonneau, Marc-Andre
contents Monocular facial performance capture in-the-wild is challenging due to varied capture conditions, face shapes, and expressions. Most current methods rely on linear 3D Morphable Models, which represent facial expressions independently of identity at the vertex displacement level. We propose SEREP (Semantic Expression Representation), a model that disentangles expression from identity at the semantic level. We start by learning an expression representation from high-quality 3D data of unpaired facial expressions. Then, we train a model to predict expression from monocular images relying on a novel semi-supervised scheme using low quality synthetic data. In addition, we introduce MultiREX, a benchmark addressing the lack of evaluation resources for the expression capture task. Our experiments show that SEREP outperforms state-of-the-art methods, capturing challenging expressions and transferring them to new identities.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14371
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargeting
Josi, Arthur
Hafemann, Luiz Gustavo
Dib, Abdallah
Got, Emeline
Cruz, Rafael M. O.
Carbonneau, Marc-Andre
Computer Vision and Pattern Recognition
Graphics
Machine Learning
Monocular facial performance capture in-the-wild is challenging due to varied capture conditions, face shapes, and expressions. Most current methods rely on linear 3D Morphable Models, which represent facial expressions independently of identity at the vertex displacement level. We propose SEREP (Semantic Expression Representation), a model that disentangles expression from identity at the semantic level. We start by learning an expression representation from high-quality 3D data of unpaired facial expressions. Then, we train a model to predict expression from monocular images relying on a novel semi-supervised scheme using low quality synthetic data. In addition, we introduce MultiREX, a benchmark addressing the lack of evaluation resources for the expression capture task. Our experiments show that SEREP outperforms state-of-the-art methods, capturing challenging expressions and transferring them to new identities.
title SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargeting
topic Computer Vision and Pattern Recognition
Graphics
Machine Learning
url https://arxiv.org/abs/2412.14371