One-shot many-to-many facial reenactment using Bi-Layer Graph Convolutional Networks

Facial reenactment is aimed at animating a source face image into a new place using a driving facial picture. In a few shot scenarios, the present strategies are designed with one or more identities or identity-sustained suffering protection challenges. These current solutions are either developed with one or more identities in mind, or face identity protection issues in one or more shot situations. Multiple pictures from the same entity have been used in previous research to model facial reenactment. In contrast, this paper presents a novel model of one-shot many-to-many facial reenactments that uses only one facial image of a face. The proposed model produces a face that represents the objective representation of the same source identity. The proposed technique can simulate motion from a single image by decomposing an object into two layers. Using bi-layer with Convolutional Neural Network (CNN), we named our model Bi-Layer Graph Convolutional Layers (BGCLN) which utilized to create the latent vector’s optical flow representation. This yields the precise structure and shape of the optical stream. Comprehensive studies suggest that our technique can produce high-quality results and outperform most recent techniques in both qualitative and quantitative data comparisons. Our proposed system can perform facial reenactment at 15 fps, which is approximately real time. Our code is publicly available at https://github.com/usaeed786/BGCLN

Armghan, AmmarCollege of Engineering, Jouf University, Sakaka, Saudi Arabia (author)
Quanyu, WangBeijing Institute of Technology, Beijing, China (author)
Alenezi, FayadhCollege of Engineering, Jouf University, Sakaka, Saudi Arabia (author)
Yue, SunBeijing Institute of Technology, Beijing, China (author)
Tiwari, Prayag,1991-Högskolan i Halmstad,Akademin för informationsteknologi(Swepub:hh)pratiw (author)
Beijing Institute of Technology, Beijing, ChinaCollege of Engineering, Jouf University, Sakaka, Saudi Arabia (creator_code:org_t)

By the author/editor: Saeed, Uzair; Armghan, Ammar; Quanyu, Wang; Alenezi, Fayadh; Yue, Sun; Tiwari, Prayag, ...

About the subject

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Electrical Engin ...; and Computer Systems

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.