Exploring StyleGAN Latent Space for Face Alignment with Limited Training Data
With deep learning models growing in size over the years, sometimes exceeding a billion parameters now, the need for large, annotated training datasets grows too. To alleviate this problem, the interest in self-supervised learning is also increasing. In this domain, with the rise of Generative Adversarial Networks (GANs) and particularly StyleGAN, the quality of image generation is significantly improving. In this paper, we propose to use StyleGAN to perform face alignment with limited training data instead of image generation. Our proposed framework Face Alignment using StyleGAN Embeddings (FASE) projects real images into StyleGAN latent space and then predicts facial landmarks from the latent vectors. Our method achieves state-of-the-art on multiple face alignment datasets in the few-shot setting.
Code (0)
등록된 구현이 없습니다.
Tasks
Face AlignmentImage GenerationSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Evolutionary latent space search for driving human portrait generation
This article presents an evolutionary approach for synthetic human portraits generation based on the latent space exploration of a generative adversarial network. The idea is to produce different human face images very s…
Face RecognitionGenerative Adversarial NetworkPaired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval
This paper investigates an open research problem of generating text-image pairs to improve the training of fine-grained image-to-text cross-modal retrieval task, and proposes a novel framework for paired data augmentatio…
Cross-Modal RetrievalData AugmentationImage to textImage-to-Text Retrieval+2Towards Kinetic Manipulation of the Latent Space
The latent space of many generative models are rich in unexplored valleys and mountains. The majority of tools used for exploring them are so far limited to Graphical User Interfaces (GUIs). While specialized hardware ca…
Towards Arbitrary Text-driven Image Manipulation via Space Alignment
The recent GAN inversion methods have been able to successfully invert the real image input to the corresponding editable latent code in StyleGAN. By combining with the language-vision model (CLIP), some text-driven imag…
AttributeImage ManipulationGrasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN
The disentanglement of StyleGAN latent space has paved the way for realistic and controllable image editing, but does StyleGAN know anything about temporal motion, as it was only trained on static images? To study the mo…
DisentanglementFace Generation