Stories
Slash Boxes
Comments

SoylentNews is people

SoylentNews is powered by your submissions, so send in your scoop. Only 19 submissions in the queue.
posted by Fnord666 on Friday May 05 2017, @06:19AM   Printer-friendly
from the next-up-is-character-assassination dept.

University of Edinburgh have used machine learning to animate human characters:

Researchers from the University of Edinburgh have developed a novel learning framework called a Phase-Functioned Neural Network (PFNN) that uses machine learning for character animation and other applications. Daniel Holden, a researcher at Ubisoft Montreal and lead researcher on this project, described PFNN as:

A learning framework that is suitable for generating cyclic behavior such as human locomotion. We also design the input and output parameters of the network for real-time data-driven character control in complex environments with detailed user interaction. Despite its compact structure, the network can learn from a large, high dimensional dataset thanks to a phase function that varies smoothly over time to produce a large variation of network configurations. We also propose a framework to produce additional data for training the PFNN where the human locomotion and the environmental geometry are coupled. Once trained our system is fast, requires little memory, and produces high quality motion without exhibiting any of the common artefacts found in existing methods.

Holden went on to say that, once trained, PFNN is extremely fast and compact, requiring only milliseconds of execution time and a few megabytes of memory, even when trained on gigabytes of motion data.

If this software can allow fewer people to create more complicated animations with less resources, it could be another step away from Hollywood. A single person with a computer could animate dead actors using software and source material (and create a soundtrack while they're at it). "Sets" can be created virtually. Personality rights laws can be circumvented by distributing amateur/fan films using the same avenues used for piracy (streaming, torrents, sneakernet, etc.), leading to a loss of control over the portrayal of living and dead actors.

Additional coverage can be found on ArsTechnica.

Related:
http://www.sciencemag.org/news/2017/05/computer-scientists-have-created-most-accurate-digital-model-human-face-here-s-what-it


Original Submission

 
This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
  • (Score: 4, Informative) by takyon on Friday May 05 2017, @01:38PM

    by takyon (881) <takyonNO@SPAMsoylentnews.org> on Friday May 05 2017, @01:38PM (#504834) Journal

    I think the industry would run into a couple of problems, mainly with the Miller test. If you're referring to child pornography, there is this [wikipedia.org]:

    In the United States, the PROTECT Act of 2003 made significant changes to the law regarding virtual child pornography.[3][4][5] Any realistic appearing computer generated depiction that is indistinguishable from a depiction of an actual minor in sexual situations or engaging in sexual acts is illegal under 18 U.S.C. § 2252A. Drawings, cartoons, sculptures, and paintings of minors in sexual situations that do not pass the Miller test were made illegal under 18 U.S.C. § 1466A.

    As for celebrities, they may be able to win in court against the pornography industry but not the broader film industry or amateurs making non-pornographic films, etc. Basically, if personality rights laws could be invalidated in the case of First Amendment protected non-porn films, but upheld for porn since porn is considered obscene and not First Amendment protected speech. So personality rights laws could morph into "don't make a CGI porno with my likeness copied and pasted into it" laws.

    --
    [SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
    Starting Score:    1  point
    Moderation   +2  
       Interesting=1, Informative=1, Total=2
    Extra 'Informative' Modifier   0  
    Karma-Bonus Modifier   +1  

    Total Score:   4