Abstract
Existing Face Re-enactment approaches have two major limitations, first, they require large dataset of images to create photo-realistic face models and second, they do not generalize well if the facial images are not available in training dataset. The generation of a new facial reenactment requires large image dataset and hours are required to train these models. Some progress in Deep Learning has shown quite significant results using Generative Adversarial Networks (GANs). Recent works in GAN have solved the problem of large dataset training dataset by introducing the concept of few-shot learning. This paper reviews existing approaches in Face Re-enactment with few-shot learning techniques and other approaches in Face Re-enactment.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
