Emo3D: Metric and Benchmarking Dataset for 3D Facial Expression Generation from Emotion Description

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Dehghani, Mahshid, Shafiee, Amirahmad, Shafiei, Ali, Fallah, Neda, Alizadeh, Farahmand, Gholinejad, Mohammad Mehdi, Behroozi, Hamid, Habibi, Jafar, Asgari, Ehsaneddin
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909333827092480
author Dehghani, Mahshid
Shafiee, Amirahmad
Shafiei, Ali
Fallah, Neda
Alizadeh, Farahmand
Gholinejad, Mohammad Mehdi
Behroozi, Hamid
Habibi, Jafar
Asgari, Ehsaneddin
author_facet Dehghani, Mahshid
Shafiee, Amirahmad
Shafiei, Ali
Fallah, Neda
Alizadeh, Farahmand
Gholinejad, Mohammad Mehdi
Behroozi, Hamid
Habibi, Jafar
Asgari, Ehsaneddin
contents Existing 3D facial emotion modeling have been constrained by limited emotion classes and insufficient datasets. This paper introduces "Emo3D", an extensive "Text-Image-Expression dataset" spanning a wide spectrum of human emotions, each paired with images and 3D blendshapes. Leveraging Large Language Models (LLMs), we generate a diverse array of textual descriptions, facilitating the capture of a broad spectrum of emotional expressions. Using this unique dataset, we conduct a comprehensive evaluation of language-based models' fine-tuning and vision-language models like Contranstive Language Image Pretraining (CLIP) for 3D facial expression synthesis. We also introduce a new evaluation metric for this task to more directly measure the conveyed emotion. Our new evaluation metric, Emo3D, demonstrates its superiority over Mean Squared Error (MSE) metrics in assessing visual-text alignment and semantic richness in 3D facial expressions associated with human emotions. "Emo3D" has great applications in animation design, virtual reality, and emotional human-computer interaction.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02049
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Emo3D: Metric and Benchmarking Dataset for 3D Facial Expression Generation from Emotion Description
Dehghani, Mahshid
Shafiee, Amirahmad
Shafiei, Ali
Fallah, Neda
Alizadeh, Farahmand
Gholinejad, Mohammad Mehdi
Behroozi, Hamid
Habibi, Jafar
Asgari, Ehsaneddin
Computer Vision and Pattern Recognition
Computation and Language
Graphics
I.2.7; I.2.10
Existing 3D facial emotion modeling have been constrained by limited emotion classes and insufficient datasets. This paper introduces "Emo3D", an extensive "Text-Image-Expression dataset" spanning a wide spectrum of human emotions, each paired with images and 3D blendshapes. Leveraging Large Language Models (LLMs), we generate a diverse array of textual descriptions, facilitating the capture of a broad spectrum of emotional expressions. Using this unique dataset, we conduct a comprehensive evaluation of language-based models' fine-tuning and vision-language models like Contranstive Language Image Pretraining (CLIP) for 3D facial expression synthesis. We also introduce a new evaluation metric for this task to more directly measure the conveyed emotion. Our new evaluation metric, Emo3D, demonstrates its superiority over Mean Squared Error (MSE) metrics in assessing visual-text alignment and semantic richness in 3D facial expressions associated with human emotions. "Emo3D" has great applications in animation design, virtual reality, and emotional human-computer interaction.
title Emo3D: Metric and Benchmarking Dataset for 3D Facial Expression Generation from Emotion Description
topic Computer Vision and Pattern Recognition
Computation and Language
Graphics
I.2.7; I.2.10
url https://arxiv.org/abs/2410.02049