Dynamic Facial Expression Generation on Hilbert Hypersphere With Conditional Wasserstein Generative Adversarial Nets

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 2; pp. 848 - 863
• Main Authors: Otberdout, Naima, Daoudi, Mohamed, Kacem, Anis, Ballihi, Lahoucine, Berretti, Stefano
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-02-2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Algorithms; Artificial Intelligence; Computer Science; Computer Vision and Pattern Recognition; conditional manifold-valued wasserstein generative adversarial networks; Curves; Dynamics; Emotion recognition; Face; Facial Expression; Facial expression generation; facial landmarks; Gallium nitride; Generative adversarial networks; Geometry; Hyperspheres; Motion; Neural Networks, Computer; Riemannian geometry; Training; Video; Videos; Riemannian geometry; Conditional manifold-valued Wasserstein Generative Adversarial Networks; Facial Landmarks; Facial expression generation
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2020.3002500

In this work, we propose a novel approach for generating videos of the six basic facial expressions given a neutral face image. We propose to exploit the face geometry by modeling the facial landmarks motion as curves encoded as points on a hypersphere. By proposing a conditional version of manifold-valued Wasserstein generative adversarial network (GAN) for motion generation on the hypersphere, we learn the distribution of facial expression dynamics of different classes, from which we synthesize new facial expression motions. The resulting motions can be transformed to sequences of landmarks and then to images sequences by editing the texture information using another conditional Generative Adversarial Network. To the best of our knowledge, this is the first work that explores manifold-valued representations with GAN to address the problem of dynamic facial expression generation. We evaluate our proposed approach both quantitatively and qualitatively on two public datasets; Oulu-CASIA and MUG Facial Expression. Our experimental results demonstrate the effectiveness of our approach in generating realistic videos with continuous motion, realistic appearance and identity preservation. We also show the efficiency of our framework for dynamic facial expressions generation, dynamic facial expression transfer and data augmentation for training improved emotion recognition models.