SoylentNews

takyon [soylentnews.org] writes:

University of Edinburgh have used machine learning to animate human characters [tomshardware.com]:

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 less 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 [soylentnews.org] using software and source material (and create a soundtrack [soylentnews.org] while they're at it). "Sets" can be created virtually [wikipedia.org]. Personality rights laws [wikipedia.org] 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.

Original Submission