Shulou(Shulou.com)11/24 Report--

CTOnews.com, Nov. 17 (Xinhua)-- A research team from Singapore's Nanyang University of Technology (NTU Singapore) recently developed a DIRFA tool that allows users to give a picture and audio content, which can automatically generate 3D video and achieve simultaneous coordination of mouth shape and sound.

DIRFA, known as DIverse yet Realistic Facial Animations, trained more than 1 million video clips of more than 6000 people, with audio clips from an open source database called the VoxCeleb2 dataset, linked to facial expressions and head movements.

Researchers say DIRFA may bring new applications in a variety of industries and areas, including healthcare, because it can improve the user experience by enabling more complex and realistic virtual assistants and chatbots.

DIRFA can also be used as a powerful tool for people with verbal or facial disabilities to help them communicate their thoughts and feelings through expressive avatars or digital representations, thereby enhancing their communication skills.

CTOnews.com attached the reference address of the paper: Rongliang Wu, Yingchen Yu, Fangneng Zhan, Jiahui Zhang, Xiaoqin Zhang, Shijian Lu. Audio-driven talking face generation with diverse yet realistic facial animations. Pattern Recognition, 2023; 144: 109865 DOI: 10.1016/j.patcog.2023.109865

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.