Deep Identity-aware Transfer of Facial Attributes

Abstract

This paper presents a Deep convolutional network model for Identity-Aware Transfer (DIAT) of facial attributes. Given the source input image and the reference attribute, DIAT aims to generate a facial image that owns the reference attribute as well as keeps the same or similar identity to the input image. In general, our model consists of a mask network and an attribute transform network which work in synergy to generate a photo-realistic facial image with the reference attribute. Considering that the reference attribute may be only related to some parts of the image, the mask network is introduced to avoid the incorrect editing on attribute irrelevant region. Then the estimated mask is adopted to combine the input and transformed image for producing the transfer result. For joint training of transform network and mask network, we incorporate the adversarial attribute loss, identity-aware adaptive perceptual loss, and VGG-FACE based identity loss. Furthermore, a denoising network is presented to serve for perceptual regularization to suppress the artifacts in transfer result, while an attribute ratio regularization is introduced to constrain the size of attribute relevant region. Our DIAT can provide a unified solution for several representative facial attribute transfer tasks, e.g., expression transfer, accessory removal, age progression, and gender transfer, and can be extended for other face enhancement tasks such as face hallucination. The experimental results validate the effectiveness of the proposed method. Even for the identity-related attribute (e.g., gender), our DIAT can obtain visually impressive results by changing the attribute while retaining most identity-aware features.

References in corpus (13)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Generative Adversarial Text to Image Synthesis
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Conditional Image Generation with PixelCNN Decoders
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Improved Training of Wasserstein GANs
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution
• Deep Convolutional Inverse Graphics Network
• Adversarial Feature Selection against Evasion Attacks
• GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
• Convolutional Network for Attribute-driven and Identity-preserving Human Face Generation

Cited by in corpus (36)

• PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy
• MaskGAN: Towards Diverse and Interactive Facial Image Manipulation
• Generative adversarial interpolative autoencoding: adversarial training on latent space interpolations encourage convex latent distributions
• GANimation: Anatomically-aware Facial Animation from a Single Image
• ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
• STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
• Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation
• Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System
• PA-GAN: Progressive Attention Generative Adversarial Network for Facial Attribute Editing
• Identity Preserving Face Completion for Large Ocular Region Occlusion
• UGAN: Untraceable GAN for Multi-Domain Face Translation
• Modular Generative Adversarial Networks
• Learning Residual Images for Face Attribute Manipulation
• Cascade EF-GAN: Progressive Facial Expression Editing with Local Focuses
• MulGAN: Facial Attribute Editing by Exemplar
• All-In-One: Facial Expression Transfer, Editing and Recognition Using A Single Network
• MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network
• A Survey of Deep Facial Attribute Analysis
• Supervised Adversarial Networks for Image Saliency Detection
• Emotion Generation and Recognition: A StarGAN Approach
• Sparsely Grouped Multi-task Generative Adversarial Networks for Facial Attribute Manipulation
• Class-Distinct and Class-Mutual Image Generation with GANs
• Face Aging with Contextual Generative Adversarial Nets
• Learning the Loss Functions in a Discriminative Space for Video Restoration
• Disentangling Pose from Appearance in Monochrome Hand Images
• Learning Symmetry Consistent Deep CNNs for Face Completion
• Perceptually Validated Precise Local Editing for Facial Action Units with StyleGAN
• Show, Attend and Translate: Unpaired Multi-Domain Image-to-Image Translation with Visual Attention
• LEED: Label-Free Expression Editing via Disentanglement
• An Efficient Integration of Disentangled Attended Expression and Identity FeaturesFor Facial Expression Transfer andSynthesis
• EvoGAN: An Evolutionary Computation Assisted GAN
• ByeGlassesGAN: Identity Preserving Eyeglasses Removal for Face Images
• 3D Dense Geometry-Guided Facial Expression Synthesis by Adversarial Learning
• ClsGAN: Selective Attribute Editing Model Based On Classification Adversarial Network
• Joint Deep Learning of Facial Expression Synthesis and Recognition
• Learn to synthesize and synthesize to learn