Convolutional Network for Attribute-driven and Identity-preserving Human Face Generation

Abstract

This paper focuses on the problem of generating human face pictures from specific attributes. The existing CNN-based face generation models, however, either ignore the identity of the generated face or fail to preserve the identity of the reference face image. Here we address this problem from the view of optimization, and suggest an optimization model to generate human face with the given attributes while keeping the identity of the reference image. The attributes can be obtained from the attribute-guided image or by tuning the attribute features of the reference image. With the deep convolutional network "VGG-Face", the loss is defined on the convolutional feature maps. We then apply the gradient decent algorithm to solve this optimization problem. The results validate the effectiveness of our method for attribute driven and identity-preserving face generation.

9 pages, 7 figures

References in corpus (7)

• Perceptual Losses for Real-Time Style Transfer and Super-Resolution
• VQA: Visual Question Answering
• DRAW: A Recurrent Neural Network For Image Generation
• Deep Convolutional Inverse Graphics Network
• Attribute2Image: Conditional Image Generation from Visual Attributes
• Transferring Landmark Annotations for Cross-Dataset Face Alignment
• What Makes Kevin Spacey Look Like Kevin Spacey

Cited by in corpus (13)

• Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images
• Deep Identity-aware Transfer of Facial Attributes
• Quantitative Digital Microscopy with Deep Learning
• Deep Learning Based Single Sample Per Person Face Recognition: A Survey
• Towards Open-Set Identity Preserving Face Synthesis
• Regularizing Deep Networks with Semantic Data Augmentation
• PA-GAN: Progressive Attention Generative Adversarial Network for Facial Attribute Editing
• DeepFaceEditing: Deep Face Generation and Editing with Disentangled Geometry and Appearance Control
• Mask-Guided Portrait Editing with Conditional GANs
• Fully-Featured Attribute Transfer
• Fast Face-swap Using Convolutional Neural Networks
• HoneyFaces: Increasing the Security and Privacy of Authentication Using Synthetic Facial Images
• 3D Face From X: Learning Face Shape from Diverse Sources