This time, Google made a splash with its “VLOGGER” technology

earthpressnews

Internet giant Google made a splash this time with its “VLOGGER” technology. This system photos are real can revive.

Google VLOGGER, prepared by researchers and presented as a research project for now, detects people in uploaded photos and can make them active in speech. Thanks to this system, people can use only a single photo. Can create virtual versions of themselves that speak realistically and can print in video format. The system, which is still not perfect for now, can also create people’s voices based on the entered recording. The system, which has the power to open big doors if it is developed a little more, It raises some concerns about abuse, but it is also reported that many precautions are being worked on in this regard. The system, which does not require special artificial intelligence model training for a good result, is developed on a data set called MENTOR, which reportedly includes more than 800,000 different people and 2,200 hours of video. It is reported that work will continue on the system, which can be used in many areas from games to content production and virtual reality.

YOU MAY BE INTERESTED IN

Before this, Google had made a splash with its artificial intelligence-based “SIMA”. SIMA (prepared by the DeepMind team)Scalable Instructable Multiworld Agent), is currently an artificial intelligence research study and is learning to play games through real games. SIMA, which DeepMind researchers worked with studios and publishers such as Hello Games (No Man’s Sky), Tuxedo Labs (Teardown) and Coffee Stain (Valheim and Goat Simulator 3), is at a level where it can play games just like us and is constantly being improved. As you can imagine, this system has a lot of potential, but There is a possibility that the infrastructure will completely change the NPCs, especially the NPCs in the game worlds..

Thanks to this system, game characters that can move more naturally and react to their environment like us can emerge, and it can increase realism incredibly by taking NPCs in these games out of predetermined routes. According to the statement, SIMA currently has approximately 600 basic skills, such as turning left / right, climbing the stairs and opening the menu to use the map. The system, which is said to be able to be instructed to perform more complex functions in a game in the future, looks really interesting and creates the impression that it will open important doors.

Google is also doing other work on games. For example Google DeepMind shortly before his team genie A system called . This system is based on the commands given It can produce playable games at a very basic level. The sensational Genie draws attention with the fact that, according to the statement, it has been trained on 200 thousand hours of game videos and can create video games from a single text command or image.

According to the information given, the system, which is not available to everyone for now and reveals a very serious potential for the future. can determine who the main character is And can allow the user to control this character in the created world. This really looks quite ambitious, it is thought that the system will be made much better graphically over time. After seeing OpenAI’s video model Sora Expectations about the future of such systems are increasing incredibly, productive artificial intelligence systems are becoming frighteningly good every day.



lgct-tech-game