ExprGAN: Facial Expression Editing with Controllable Expression Intensity

Abstract

Facial expression editing is a challenging task as it needs a high-level semantic understanding of the input face image. In conventional methods, either paired training data is required or the synthetic face resolution is low. Moreover, only the categories of facial expression can be changed. To address these limitations, we propose an Expression Generative Adversarial Network (ExprGAN) for photo-realistic facial expression editing with controllable expression intensity. An expression controller module is specially designed to learn an expressive and compact expression code in addition to the encoder-decoder network. This novel architecture enables the expression intensity to be continuously adjusted from low to high. We further show that our ExprGAN can be applied for other tasks, such as expression transfer, image retrieval, and data augmentation for training improved face expression recognition models. To tackle the small size of the training database, an effective incremental learning scheme is proposed. Quantitative and qualitative evaluations on the widely used Oulu-CASIA dataset demonstrate the effectiveness of ExprGAN.

Cited by in corpus (25)

• FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals
• Face Recognition: From Traditional to Deep Learning Methods
• Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets
• Adversarial Training in Affective Computing and Sentiment Analysis: Recent Advances and Perspectives
• F3A-GAN: Facial Flow for Face Animation with Generative Adversarial Networks
• Conditional Adversarial Synthesis of 3D Facial Action Units
• Cascade EF-GAN: Progressive Facial Expression Editing with Local Focuses
• Audio-Driven Emotional Video Portraits
• Mining Generalized Features for Detecting AI-Manipulated Fake Faces
• Facial Expression Editing with Continuous Emotion Labels
• Automated Deepfake Detection
• Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
• Morphset:Augmenting categorical emotion datasets with dimensional affect labels using face morphing
• Perceptually Validated Precise Local Editing for Facial Action Units with StyleGAN
• A Layer-Based Sequential Framework for Scene Generation with GANs
• LEED: Label-Free Expression Editing via Disentanglement
• An Efficient Integration of Disentangled Attended Expression and Identity FeaturesFor Facial Expression Transfer andSynthesis
• Emotion Transfer Using Vector-Valued Infinite Task Learning
• On the use of automatically generated synthetic image datasets for benchmarking face recognition
• Continual Learning for Affective Computing
• Inducing Optimal Attribute Representations for Conditional GANs
• Synthetic Expressions are Better Than Real for Learning to Detect Facial Actions
• Gated SwitchGAN for multi-domain facial image translation
• Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling
• Joint Deep Learning of Facial Expression Synthesis and Recognition