CACM Jan. 2019 - Face2Face Real Time Face Capture and Reenactment of RGB Videos

Рет қаралды 9,190

Association for Computing Machinery (ACM)

5 жыл бұрын

Face2Face is an approach for real-time facial reenactment of a monocular target video sequence (e.g., KZfaq video). The source sequence is also a monocular video stream, captured live with a commodity webcam. This video and accompanying article present research with the goal of developing methods for animating facial expressions of the target video by a source actor and re-render the manipulated output video in a photo-realistic fashion. The result is a convincing re-render okf the synthesized target face on top of the corresponding video stream that seamlessly blends with the real-world illumination. In this video, Justus Thies discusses "Face2Face: Real-Time Face Capture and Reenactment of RGB Videos," a Research Highlights article in the January 2019 Communications of the ACM.
Read the full article here: cacm.acm.org/magazines/2019/1/233531-face2face/fulltext

Пікірлер: 4

@WrestlingTracksTV 5 жыл бұрын

where is the software

@theotherme4120 5 жыл бұрын

so we are going to have to trust some company to tell us which video is fake and which is real ?

@armanke13 5 жыл бұрын

Didn't movies have done this many times? (I think of Thanos and Hulk in Marvel movies). But maybe the tech is proprietary, 🤔

@feuillufantastouille9022 5 жыл бұрын

The facial expression capture part is not new, but the mapping on a video is. it is easier to animate a 3D model than modifying a 2D video realistically.