2024/10/02 by Dehghani, Mahshid, Shafiee, Amirahmad, Shafiei, Ali +6
#Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Graphics (cs.GR) #I.2.10 #I.2.7
paper · doi:10.48550/arxiv.2410.02049
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.