PortraitGAN for Flexible Portrait Manipulation

Abstract

Previous methods have dealt with discrete manipulation of facial attributes such as smile, sad, angry, surprise etc, out of canonical expressions and they are not scalable, operating in single modality. In this paper, we propose a novel framework that supports continuous edits and multi-modality portrait manipulation using adversarial learning. Specifically, we adapt cycle-consistency into the conditional setting by leveraging additional facial landmarks information. This has two effects: first cycle mapping induces bidirectional manipulation and identity preserving; second pairing samples from different modalities can thus be utilized. To ensure high-quality synthesis, we adopt texture-loss that enforces texture consistency and multi-level adversarial supervision that facilitates gradient flow. Quantitative and qualitative experiments show the effectiveness of our framework in performing flexible and multi-modality portrait manipulation with photo-realistic effects.

References in corpus (15)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Toward Multimodal Image-to-Image Translation
• Pose Guided Person Image Generation
• Unsupervised Image-to-Image Translation Networks
• Adversarial Discriminative Domain Adaptation
• Age Progression/Regression by Conditional Adversarial Autoencoder
• Deep Photo Style Transfer
• GANimation: Anatomically-aware Facial Animation from a Single Image
• Visual Attribute Transfer through Deep Image Analogy
• Everybody Dance Now
• Unsupervised Person Image Synthesis in Arbitrary Poses
• Facelet-Bank for Fast Portrait Manipulation