Dual Encoder-Decoder based Generative Adversarial Networks for Disentangled Facial Representation Learning

TL;DR

This paper introduces DED-GAN, a novel dual encoder-decoder architecture for disentangled facial representation learning, improving pose-invariant recognition and face synthesis by integrating continuous pose estimation and Wasserstein loss.

Contribution

The paper proposes a dual encoder-decoder GAN framework that effectively disentangles pose and identity in facial images, with continuous pose modeling and improved training stability.

Findings

Outperforms state-of-the-art in pose-invariant face recognition

Achieves high-quality face synthesis across poses

Demonstrates robustness on diverse datasets

Abstract

To learn disentangled representations of facial images, we present a Dual Encoder-Decoder based Generative Adversarial Network (DED-GAN). In the proposed method, both the generator and discriminator are designed with deep encoder-decoder architectures as their backbones. To be more specific, the encoder-decoder structured generator is used to learn a pose disentangled face representation, and the encoder-decoder structured discriminator is tasked to perform real/fake classification, face reconstruction, determining identity and estimating face pose. We further improve the proposed network architecture by minimising the additional pixel-wise loss defined by the Wasserstein distance at the output of the discriminator so that the adversarial framework can be better trained. Additionally, we consider face pose variation to be continuous, rather than discrete in existing literature, to inject richer pose information into our model. The pose estimation task is formulated as a regression problem, which helps to disentangle identity information from pose variations. The proposed network is evaluated on the tasks of pose-invariant face recognition (PIFR) and face synthesis across poses. An extensive quantitative and qualitative evaluation carried out on several controlled and in-the-wild benchmarking datasets demonstrates the superiority of the proposed DED-GAN method over the state-of-the-art approaches.