Presented at the 31st Conference on Graphics, Patterns and Images (SIBGRPI) – Awarded with an Honorable Mention
Summary: Modern motion capturing systems can accurately store human motion with high precision. Editing this kind of data is troublesome, due to the amount and complexity of data. In this paper, we present a method for decoupling the aspects of human motion that are strictly related to locomotion and balance, from other movements that may convey expressiveness and intentionality. We then demonstrate how this decoupling can be useful in creating variations of the original motion, or in mixing different actions together.
About three weeks ago Fabric Software abruptly ended the development of Fabric Engine without any following announcements. In this second post of a two-post series, I’ll try to go over why Fabric was a great fit for Machine Learning in the context of 3d Content Creation (animation, games and VFX). Bear in mind these are my own personal opinions.
AI, beyond the hype
Nowadays the acronym AI (artificial intelligence) seems to be everywhere. AI cars, AI stealing your job, processing AI in your GPU, and so on… Not unusually you see the buzzword AI alongside stuff that has no direct relation to artificial intelligence, like this tweet in which the WSJ uses VR goggles to depict AI.
VR goggles used to depict the concept of AI (credit: WSJ, Twitter)
Most of the times when people talk about AI, they are really talking about a rapidly developing segment of AI called Machine Learning (ML). Machine Learning is a field in computer science that is interested in techniques that make it possible to program computers with data, instead of using explicit instructions. ML techniques are either based on a statistical approach or a connectionist approach. The connectionist approach is in vogue nowadays, especially a specific approach known as Deep Learning.
Data is what makes ML tick. This data can be of two kinds: labeled and unlabeled. Unlabeled data can be used to find patterns within the data itself. A very nice example of the use of ML with unlabeled data in a 3d content creation setting is the work of Loper et al. (2015). The authors used a dataset consisting of 2000 scanned human bodies (per gender) and, using a statistical technique called PCA, found that they could describe scanned bodies with less than 5% error using only 10 blendshapes. You can experiment with the results of this work in Maya, clicking here.
The three principal components of the human shape (credit: Loper et al. 2015)
This month I complete one year teaching at UFSC, in celebration of this I wanted to share the work of some of the students in one of my classes: 3d Animation I or EGR7249. This is the first contact of the students with the art of 3d animation in the course. Congratulations to all students for the effort and great work.
In the middle of production I was face’d with something I had not done yet. We had to constraint a bunch of strands to the tip of another strand. As in the time we did not have Syflex for ICE we decided to use ICE’s own strand framework. Good for us it was not hard arranging a bunch of nodes in order to get this constraint going.
All I had to do to share it online was to make it a little more flexible and scale friendly. Here it is hope you like it.