English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

One-shot talking face generation aims at synthesizing a high-quality talkingface video from an arbitrary portrait image, driven by a video or an audiosegment. One challenging quality factor is the resolution of the output video:higher resolution conveys more details. In this work, we investigate the latentfeature space of a pre-trained StyleGAN and discover some excellent spatialtransformation properties. Upon the observation, we explore the possibility ofusing a pre-trained StyleGAN to break through the resolution limit of trainingdatasets. We propose a novel unified framework based on a pre-trained StyleGANthat enables a set of powerful functionalities, i.e., high-resolution videogeneration, disentangled control by driving video or audio, and flexible faceediting. Our framework elevates the resolution of the synthesized talking faceto 1024*1024 for the first time, even though the training dataset has a lowerresolution. We design a video-based motion generation module and an audio-basedone, which can be plugged into the framework either individually or jointly todrive the video generation. The predicted motion is used to transform thelatent features of StyleGAN for visual animation. To compensate for thetransformation distortion, we propose a calibration network as well as a domainloss to refine the features. Moreover, our framework allows two types of facialediting, i.e., global editing via GAN inversion and intuitive editing based on3D morphable models. Comprehensive experiments show superior video quality,flexible controllability, and editability over state-of-the-art methods.

StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN