DrFER: Learning Disentangled Representations for 3D Facial Expression Recognition
This addresses the issue of compromised expression distinctiveness in 3D FER for applications in facial analysis, representing an incremental improvement over prior disentanglement methods.
The paper tackled the problem of entangled expression and identity features in 3D facial expression recognition by introducing DrFER, a method that uses a dual-branch framework for disentangled representation learning, achieving superior performance on BU-3DFE and Bosphorus datasets.
Facial Expression Recognition (FER) has consistently been a focal point in the field of facial analysis. In the context of existing methodologies for 3D FER or 2D+3D FER, the extraction of expression features often gets entangled with identity information, compromising the distinctiveness of these features. To tackle this challenge, we introduce the innovative DrFER method, which brings the concept of disentangled representation learning to the field of 3D FER. DrFER employs a dual-branch framework to effectively disentangle expression information from identity information. Diverging from prior disentanglement endeavors in the 3D facial domain, we have carefully reconfigured both the loss functions and network structure to make the overall framework adaptable to point cloud data. This adaptation enhances the capability of the framework in recognizing facial expressions, even in cases involving varying head poses. Extensive evaluations conducted on the BU-3DFE and Bosphorus datasets substantiate that DrFER surpasses the performance of other 3D FER methods.