Abstract: We present a real‐time system for character control that relies on the classification of locomotive actions in skeletal motion capture data. Our method is both progress dependent and style invariant. Two deep neural networks are used to correlate body shape and implicit dynamics to locomotive types and their respective progress. In comparison to related work, our approach does not require a setup step and enables the user to act in a natural, unconstrained manner. Also, our method displays better performance than the related work in scenarios where the actor performs sharp changes in direction and highly stylized motions while maintaining at least as good performance in other scenarios. Our motivation is to enable character control of non‐bipedal characters in virtual production and live immersive experiences, where mannerisms in the actor’s performance may be an issue for previous methods.
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.
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.
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.
This last job I’ve participated in was of a very rare breed. Animaking was bold enough to mix a bunch of different techniques, namely live action, miniature models, stop motion, cg and post… phew. It all blends into a nice view of the Aircross automobile running through the atacama desert…
I was a small part of this great effort, running most particle sims. It was very nice to work with some old friends and meet a few more nice people.
Watch in HD, if you will…
Simple script emulating 3ds Max’s behaviour of offseting animation through transforms inside of Softimage.
Add-on: Offset Curves.xsiaddon
Back from the metropolis! This past week I have presented a workshop on ICE for 40 people at Melies school of cinema and animation, in São Paulo. Those who attended got a clear idea of what a interactive visual programing envoiroment like ICE may bring to the table in the context of animation and effects. We also stablished a panorama of most type of sims that exist in this, and other plataforms, trying to understand the pros and cons of each. Besides this overview we got into the guts of all the math behind ICE and some things those who are not aquinted with the tool get a hard time with (like data’s type and context). To finish it all off tornados and explosions were simulated, good times!
This is an oldie actually. A compound that restores lost symmetry, as long as you have been a good boy and kept a symmetry map.
Compound: Restore Symmetry.xsicompound