using real people in actual locations when creating a video is an example of: This is a topic that many people are looking for. thetruthaboutdow.org is a channel providing useful information about learning, life, digital marketing and online courses …. it will help you have an overview and solid multi-faceted knowledge . Today, thetruthaboutdow.org would like to introduce to you Fake videos of real people — and how to spot them Supasorn Suwajanakorn . Following along are instructions in the video below:
“At these images now tell me. Which obama here is real video. Barack obama to to help families nrefinance their homes to invest in things nlike high tech manufacturing. Clean and the infrastructure.
Nthat creates good new jobs supasorn suwajanakorn. Anyone the answer is none of them laughter. None of these is actually real so let me tell you how we got here my inspiration for this work was a project meant to preserve our last nchance for learning about the holocaust from the survivors. It s called new dimensions in testimony and it allows you to have ninteractive conversations with a hologram nof.
A real holocaust. Survivor video man how did you nsurvive. The holocaust. Video hologram.
How did i survive. I survived. I believe because providence watched over me ss turns out these answers nwere prerecorded in a studio. Yet the effect is astounding you feel so connected to his story nand to him as a person.
I think there s something special nabout human interaction that makes it much more profound and personal than what books or lectures. Nor movies could ever teach us so i saw this and began to wonder can we create a model nlike this for anyone a model that looks talks nand acts. Just like them so i set out to see if this could be done and eventually came up with a new solution that can build a model of a person nusing nothing. But these existing photos and videos of a person.
If you can leverage nthis kind of passive information. Just photos and video that are out there that s the key to scaling to anyone by the way here s richard feynman. Who in addition to being na nobel prize winner in physics. Was also known as a legendary teacher wouldn t it be great nif.
We could bring him back to give his lectures nand inspire millions of kids perhaps not just in english nbut in any language or if you could ask our grandparents nfor advice and hear those comforting words even if they re no longer with us or maybe. Using this tool. Nbook authors. Alive or not could read aloud all of their books.
Nfor. Anyone. Interested the creative possibilities. Nhere are endless and to me.
That s very exciting and here s how it s working. So far first. We introduce a new technique that can reconstruct a high detailed n3d face model from any image without ever 3d scanning the person and here s the same output model nfrom different views this also works on videos by running the same algorithm non each video frame and generating a moving 3d model and here s the same noutput model from different angles it turns out this problem nis. Very challenging.
But the key trick nis that we are going to analyze a large photo collection nof. The person beforehand for george w. Bush nwe can just search on google and from that we are able nto build an average model an iterative refined model nto recover the expression in fine details nlike creases and wrinkles. What s fascinating about this is that the photo collection ncan come from your typical photos.
It doesn t really matter nwhat expression. You re making or where you took those photos. What matters is nthat there are a lot of them. And we are still missing color here.
So next we develop na new blending technique that improves. Upon na single averaging method and produces sharp nfacial textures and colors. And this can be done for any expression. Now we have a control nof a model of a person and the way it s controlled now nis by a sequence of static photos notice how the wrinkles come and go ndepending on the expression.
We can also use a video nto drive the model video daniel craig right. But somehow we ve managed to attract nsome more amazing. People ss and here s another fun demo. So what you see here nare controllable models of people.
I built nfrom their internet photos. Now if you transfer nthe motion from the input video. We can actually drive the entire party george w. Bush nit s a difficult bill to pass because there s a lot of moving parts and the legislative processes can be ugly applause ss so coming back a little bit our ultimate goal rather nis to capture their mannerisms or the unique way each nof these people talks and smiles.
So to do that can we nactually teach the computer to imitate the way someone talks by only showing it nvideo footage of the person. And what i did exactly was ni let a computer watch 14 hours of pure barack obama ngiving addresses and here s what we can produce ngiven only his audio video. Bo the results are clear america s businesses have created n145 million new jobs over 75 straight months ss. So what s being synthesized here nis.
Only the mouth region and here s how we do it our pipeline uses a neural network to convert and input audio ninto these mouth points video bo we get it through our job nor through medicare or medicaid ss then we synthesize the texture nenhance details and teeth and blend it into the head nand background from a source video video bo women can get free checkups and you can t get charged more njust for being a woman. Young people can stay non. A parent s plan until they turn 26 ss. I think these results nseem very realistic and intriguing.
But at the same time nfrightening even to me our goal was to build an accurate model nof a person not to misrepresent them. But one thing that concerns me nis its potential for misuse people have been thinking nabout this problem for a long time since the days when photoshop nfirst hit the market as a researcher. I m also working non countermeasure technology. And i m part of an ongoing neffort at ai foundation.
Which uses a combination nof machine. Learning and human moderators to detect fake images and videos fighting against my own work and one of the tools. We plan to release nis called reality defender. Which is a web browser plug in nthat can flag potentially fake content automatically right in the browser applause despite all this though fake videos could do a lot of damage even before anyone has a chance to verify so it s very important nthat.
We make everyone aware of what s currently possible so we can have the right assumption nand. Be critical about what we see there s still a long way to go before nwe can fully model individual people and before we can ensure nthe safety of this technology. But i m excited and hopeful because if we use it right and carefully this tool can allow any individual s npositive impact on the world to be massively scaled and really help shape our future nthe way. We want it to be thank you ” .
Thank you for watching all the articles on the topic Fake videos of real people — and how to spot them Supasorn Suwajanakorn . All shares of thetruthaboutdow.org are very good. We hope you are satisfied with the article. For any questions, please leave a comment below. Hopefully you guys support our website even more.
“Do you think you re good at spotting fake videos, where famous people say things they ve never said in real life? See how they re made in this astonishing talk and tech demo. Computer scientist Supasorn Suwajanakorn shows how, as a grad student, he used AI and 3D modeling to create photorealistic fake videos of people synced to audio. Learn more about both the ethical implications and the creative possibilities of this tech — and the steps being taken to fight against its misuse.nnCheck out more TED Talks: http://www.ted.comnnThe TED Talks channel features the best talks and performances from the TED Conference, where the world s leading thinkers and doers give the talk of their lives in 18 minutes (or less). Look for talks on Technology, Entertainment and Design — plus science, business, global issues, the arts and more.nnFollow TED on Twitter: http://www.twitter.com/TEDTalksnLike TED on Facebook: https://www.facebook.com/TEDnnSubscribe to our channel: https://www.youtube.com/TED”,
TEDTalk, TEDTalks, AI, machine learning, technology, invention, future, media, politics, history, software, computers