Capturing Dynamics: The 4D Facial Expression Intensity Dataset

2026-10-01

AI Summary

This study addresses the limitations of traditional 2D static images in facial expression intensity estimation, which neglect three-dimensional geometry and temporal continuity, by proposing a novel paradigm based on 4D dynamic expression perception. Leveraging parametric face models to synthesize high-fidelity, spatiotemporally coherent mesh sequences, this work constructs 4DFEID, the first naturalistic dynamic expression analysis benchmark dataset comprising 2,869 sequences and over 90,000 crowdsourced ratings. Furthermore, a spatiotemporal graph neural network baseline is designed for multimodal aggregation optimization. Experimental results demonstrate that this spatiotemporal graph architecture significantly outperforms conventional frame-level aggregation methods. By bridging the gap caused by the absence of dynamic expression benchmarks in affective computing, this research establishes a new paradigm for human-computer interaction and affective perception studies.

Abstract

The estimation and analysis of facial expression intensity play a crucial role in affective communication and human-computer interaction. Previous research has primarily focused on detecting and estimating facial expression intensity from frame-level 2D representations. However, this limitation restricts a comprehensive understanding of real-world facial expressions, as they are inherently 3D and temporally continuous. This paper investigates the perception of facial expression intensity by introducing the 4D Facial Expression Intensity Dataset (4DFEID). We employ a parametric face model and compile a total of 2,869 mesh sequences with controlled geometric variations, generating 4D data instances with diverse peak intensities and identity attributes. Using a Likert scale, we collect more than 90,000 subjective intensity perception ratings via a crowdsourcing platform. We explore various architectures and aggregation methods to establish baselines for episode intensity estimation on the new dataset, revealing that spatial-temporal graph models consistently outperform traditional frame-aggregation methods. In contrast to existing datasets that rely on 2D static imagery, the proposed 4D-FEID dataset provides the community with a unique and vital resource for investigating the perception of facial expression intensity through the use of dynamic 3D stimuli. By offering high-fidelity, spatio-temporally coherent facial data, 4D-FEID establishes a new foundation for research into more nuanced and naturalistic expression analysis, thereby addressing a gap in the current landscape of affective computing and human-computer interaction studies. The dataset is available at link.

Problem

• facial expression intensity
• 4D facial data
• affective computing
• human-computer interaction
• dynamic 3D stimuli

Innovation

• 4D Facial Expression Intensity Dataset
• Parametric Face Model
• Spatial-Temporal Graph Models
• Expression Intensity Perception
• Affective Computing