تقرير
MyStyle: A Personalized Generative Prior
العنوان: | MyStyle: A Personalized Generative Prior |
---|---|
المؤلفون: | Nitzan, Yotam, Aberman, Kfir, He, Qiurui, Liba, Orly, Yarom, Michal, Gandelsman, Yossi, Mosseri, Inbar, Pritch, Yael, Cohen-or, Daniel |
سنة النشر: | 2022 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Graphics, Computer Science - Machine Learning |
الوصف: | We introduce MyStyle, a personalized deep generative prior trained with a few shots of an individual. MyStyle allows to reconstruct, enhance and edit images of a specific person, such that the output is faithful to the person's key facial characteristics. Given a small reference set of portrait images of a person (~100), we tune the weights of a pretrained StyleGAN face generator to form a local, low-dimensional, personalized manifold in the latent space. We show that this manifold constitutes a personalized region that spans latent codes associated with diverse portrait images of the individual. Moreover, we demonstrate that we obtain a personalized generative prior, and propose a unified approach to apply it to various ill-posed image enhancement problems, such as inpainting and super-resolution, as well as semantic editing. Using the personalized generative prior we obtain outputs that exhibit high-fidelity to the input images and are also faithful to the key facial characteristics of the individual in the reference set. We demonstrate our method with fair-use images of numerous widely recognizable individuals for whom we have the prior knowledge for a qualitative evaluation of the expected outcome. We evaluate our approach against few-shots baselines and show that our personalized prior, quantitatively and qualitatively, outperforms state-of-the-art alternatives. Comment: SIGGRAPH ASIA 2022, Project webpage: https://mystyle-personalized-prior.github.io/, Video: https://youtu.be/QvOdQR3tlOc |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2203.17272 |
رقم الأكسشن: | edsarx.2203.17272 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!