Logo Logo
deutsch
directory schraeg
Knowledge
Codecs
Hardware
Camcorders· Cinema-Kamera· Computers· Drohnen· GPU· Kamera-Zubehör· Video-DSLR· accessories
Software
Compositing· Color correction· DV Editing
DV-Movies

HowTo
Shooting· Sound
Misc
Forschung· Reviews· Streaming
/// News
Artificial intelligence controlled - GANs with semantic interpolation

Artificial intelligence controlled - GANs with semantic interpolation

[10:33 sat,24.October 2020   by ]    

Two Minute Papers has once again summarized an important current AI development in a visually appealing way for everyone. This time it&s about semantic interpolation or in English original: Semantic Interpolation.

In contrast to classical morphing, a trained AI (ideally) has an extended understanding of the entered scene. If it recognizes that the scene is a face or a building, it can also conclude that there is probably another ear on the side of the face that is away from the camera. Or that behind a closed mouth, tongue and teeth are also visible when the mouth opens.



GAN_interpolation



Semantic interpolation is about creating images in a relatively arbitrary way, not only with a current AI architecture (like faces e.g. with simple GANs). But the generation of images can be controlled more concretely. Typically, this is achieved by changing vectors in the so-called latent space, but as in a special case shown in the video, another image can be used as style input for properties.

You can imagine this in a way that the first image provides a "basic" face as a basis and the second image "contributes" properties like skin color, glasses, mouth opening and/or head rotation. The second image thus describes the "semantic properties", or their intended state.

The semantic interpolation now goes one step further and allows - if the semantic properties are correctly trained in the latent space - to switch between semantic properties. This means to change head turns or mouth opening in a targeted way. Or to add glasses. Or to age or rejuvenate faces.

And once an AI has learned which properties change an object in which way, it is possible to achieve significantly improved morphings in which almost every intermediate image is a passable result. Even if the source and final image differ very much.


Link more infos at bei www.youtube.com

deutsche Version dieser Seite: Künstliche Intelligenz morpht Bilder besser mit semantischer Interpolation

  

  Vorige News lesen Nächste News lesen 
bildNeue HP DreamColor HP Z25xs G3 und Z27xs G3Monitore mit DisplayHDR 600 und 2x USB-C bildAdobe Bridge bekommt Integration in Premiere Pro und Media Encoder


related news:1E0Nvidia AI Video Compression saves streaming data rate with artificial intelligence 7.October 2020
Neural Compression to try out HiFiC- High-Fidelity Generative Image Compression 20.September 2020
Colourlab Ai wants to revolutionize color correction with artificial intelligence 11.September 2020
Neural network DAIN interpolates stop-motion frames 9.September 2020
Automatic transcription: Transcriptive Plugin becomes cheaper per minute with prepaid option 22.March 2020
The new THX trailer Deep Note 2019 is ready - made by Andrew Kramer! 22.August 2019
Edit the words of a speaker in a video using a text editor // Siggraph 2019 24.June 2019
alle Newsmeldungen zum Thema Machine Learning


[nach oben]
















Archiv Newsmeldungen

2020

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

2019
December - November - October - September - August - July - June - May - April - March - February - January

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

2003

2002

2001

2000






































deutsche Version dieser Seite: Künstliche Intelligenz morpht Bilder besser mit semantischer Interpolation



last update : 4.Dezember 2020 - 18:02 - slashCAM is a project by channelunit GmbH- mail : slashcam@--antispam:7465--slashcam.de - deutsche Version