Semi-Latent GAN: Learning to generate and modify facial images from attributes
Generating and manipulating human facial images using high-level attributal controls are important and interesting problems. The models proposed in previous work can solve one of these two problems (generation or manipulation), but not both coherently. This paper proposes a novel model that learns how to both generate and modify the facial image from high-level semantic attributes. Our key idea is to formulate a Semi-Latent Facial Attribute Space (SL-FAS) to systematically learn relationship between user-defined and latent attributes, as well as between those attributes and RGB imagery. As part of this newly formulated space, we propose a new model --- SL-GAN which is a specific form of Generative Adversarial Network. Finally, we present an iterative training algorithm for SL-GAN. The experiments on recent CelebA and CASIA-WebFace datasets validate the effectiveness of our proposed framework. We will also make data, pre-trained models and code available.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeGenerative Adversarial NetworkSimilar Papers 제목 키워드 기반
CONTROLLING THE MEMORABILITY OF REAL AND UNREAL FACE IMAGES
Every day, we are bombarded with many face photographs, whether on social media, television, or smartphones. From an evolutionary perspective, faces are intended to be remembered, mainly due to survival and personal rel…
AttributeText-Driven Image Manipulation via Semantic-Aware Knowledge Transfer
Semantic-level facial attribute transfer is a special task to edit facial attribute, when reference images are viewed as conditions to control the image editing. In order to achieve better performance, semantic-level fac…
AttributeImage ManipulationTransfer LearningGANalyzer: Analysis and Manipulation of GANs Latent Space for Controllable Face Synthesis
Generative Adversarial Networks (GANs) are capable of synthesizing high-quality facial images. Despite their success, GANs do not provide any information about the relationship between the input vectors and the generated…
AttributeFace GenerationImage GenerationProminent Attribute Modification using Attribute Dependent Generative Adversarial Network
Modifying the facial images with desired attributes is important, though challenging tasks in computer vision, where it aims to modify single or multiple attributes of the face image. Some of the existing methods are eit…
AttributeGenerative Adversarial NetworkCLOAK: Contrastive Guidance for Latent Diffusion-Based Data Obfuscation
Data obfuscation is a promising technique for mitigating attribute inference attacks by semi-trusted parties with access to time-series data emitted by sensors. Recent advances leverage conditional generative models toge…
Contrastive Learning