As Artificial Intelligence rages through all industries, most of the creative people in creative industries, think that they are more or less secure and that they will keep their status quo, unaffected by the AI’s Storm.
What is the problem? That not all the tasks within the boundaries of the creativity are purely creative, and there are plenty of manual and repetitive tasks that could benefit from applying new and innovative technologies, to push forward the boundaries of what is possible to do now a days without the need of counting witha large team.
Machine learning can improve drastically processes like rigging and animating characters, animals and objects within the scope of a game, which would allow to save funds and make the process more accessible to other different industries.
The following article debates on this idea and proposes a couple of solutions that shoul be ready in the course of the months to come.
Once upon a time, a young boy named Ed nursed a wild ambition to become a feature-film animator. He loved Disney’s Peter Pan and Pinocchio, and could not imagine a more magical way of leading life. But by the time he reached college, he realised there was one big problem: he couldn’t draw well enough.
Both Peter Pan and Pinocchio were flat, hand-sketched, two-dimensional movies. This meant that its artists had worked long and hard at sketching each frame. They had painstakingly drawn each character posing slightly differently than in the previous scene, and then some more, and some more…
In case you want to try it, there are already some open source and commercial solutions that will allow you to take advantage of the full power of artificial intelligence to create the animations for your project.
Neural State Machine for Character-Scene Interactions
This project explores the opportunities of deep learning for character animation and control as part of my Ph.D. research at the University of Edinburgh in the School of Informatics, supervised by Taku Komura. Over the last couple years, this project has become a modular and stable framework for data-driven character animation, including data processing, network training and runtime control, developed in Unity3D / Tensorflow / PyTorch. This repository enables using neural networks for animating biped locomotion, quadruped locomotion, and character-scene interactions with objects and the environment. Further advances on this research will continue to be added to this project.