Logo Logo
directory schraeg
Camcorders· Cinema-Kamera· Computers· Video-DSLR· accessories
Compositing· Color correction· DV Editing

Shooting· Sound
/// News
Put in the mouth: artificial intelligence renders mouth after audio file

Put in the mouth: artificial intelligence renders mouth after audio file

[11:34 fri,14.July 2017   by ]    

The SIGGRAPH 2017 already throws back its shadows, and the topic of artificial intelligence also occupies an ever-widening place within the framework of the presented research results. A good example is the GRAIL (Computer Graphics and Imaging Laboratory, University of Washington's Department of Computer Science and Engineering). PIC1 In this, the mouth movement of a video recording by Barack Obama was generated synthetically by Barack Obama in another video recording. If you do not know this before, one of the newly generated video clip is authentic. For a better understanding, here is a more detailed explanation of the project: VY = 9Yq67CjDqvw That such a technology is now available brings a lot of implications: First of all, the basic credibility of video material is destroyed. And this should indirectly also increase the mistrust of the media. The only possible solution is the digital signature of a video file. So similar to the cryptoerations and the blockchain could be a video file with hashed hash values u200bu200bas genuine sign. A subsequent manipulation would be immediately recognizable because the signature no longer fits. These keys must of course also originate from trustworthy sources. This sounds as if a completely new market (also for camera manufacturers) could arise. But also in the artistic sense the technology could be interesting. Particularly in the case of post-synchronization, a German translation could be made at the same timeCorrect lip movements. And conversely, the export of German film to the English-speaking region could be fired. Because it is often said that especially Americans are extremely allergic to synchro-responses, if the lip movements do not fail exactly. And last but not least, this technology could also help in principle, instead of O-Ton in scenic productions the voices in the post easier to use overdub. Even smaller language errors (which would otherwise make a scene equally useless) could be thereby comfortably ironed, by the lips times briefly automated. (T) yes, people, it will come so whether we want or not ... u003cimg src=


  Vorige News lesen Nächste News lesen 
bildAMD nennt Preise und Termine für Ryzen 3 und Threadripper bildEdelkrone Steady Module für ruhigere, manuelle Slider-Fahrten

related news:1E0Apogee MiC Plus: USB microphone with headphone output 20.November 2017
Red Giant Universe 2.2 -- Plugin-Update with 11 new transitions 15.November 2017
Atomos 8.42 update for Shogun Inferno with 6G compatibility for Panasonic EVA1, Alexa Mini and other 14.November 2017
SmallHD OS3 big Firmware Update with new False Color, Spot-Meter (Waveform) functions and much more. 13.November 2017
Asus ROG G703 Power-Notebook: 4.3 GHz i7-7820HK CPU, GTX 1080 and 4.400 MB/s SSD 12.November 2017
AMD's GPU Architect switches to Intel: High-End GPUs 10.November 2017
Intel's next CPU comes with an integrated AMD graphics unit! 6.November 2017
alle Newsmeldungen zum Thema PC
1E0Apogee MiC Plus: USB microphone with headphone output 20.November 2017
Google Resonance Audio: 3D Sound SDK for VR and AR 11.November 2017
Adobe SneakPeak: visual Tools for 360° Audio/Video Authoring in the works 23.October 2017
Adobe CC 2018 stops native support for Dolby audio 19.October 2017
Premium Beat gives away 119 sound effects 8.October 2017
Sound Devices MixPre-10T: New 12 Track Audio Recorder/Mixer with 10 Inputs 5.October 2017
Interviewclip: Canon XF400 and XF405: 4K Cams with 60p, XLR and much more. // IBC 2017 20.September 2017
alle Newsmeldungen zum Thema Sound

[nach oben]

Archiv Newsmeldungen


November - October - September - August - July - June - May - April - March - February - January

December - November - October - September - August - July - June - May - April - March - February - January

















deutsche Version dieser Seite: In den Mund gelegt: Künstliche Intelligenz rendert Mund nach Audio-Datei

last update : 22.November 2017 - 18:00 - slashCAM is a project by channelunit GmbH- mail : slashcam@--antispam:7465--slashcam.de - deutsche Version