Animation Programmer
Montreal
Joined July 2009
- Tweets320
- Following469
- Followers1.5K
- Likes377
Simon Clavet retweeted
Simon Clavet is bringing his talent to TiMi Studio Group!
A pioneer in procedural animation for gaming, he now joins our TiMi Montreal team to help us get our unannounced AAA open world multiplayer project in the hands of gamers worldwide.
#montreal #gamedev #videogameindustry
Simon Clavet retweeted
How can we measure the cost of transitioning between two different animations? In this blog post I propose a solution based on the assumption of inertialization blending - involving (as usual) some playing around with spring equations!
theorangeduck.com/page/inert…
A couple years ago I was dancing on 'uptown funk' in a mocap suit with @anorangeduck and @_Quazi_. The goal was to find a way to play any move on a non-cheating ragdoll (or a real robot). Good job guys. It worked.
This quoted post is unavailable.
Simon Clavet retweeted
I've just added a basic implementation of Learned Motion Matching to my previous Motion Matching demo. Hopefully useful to anyone working on this stuff. Results aren't visually any different (as intended), but still cool to see LMM running in the browser!
github.com/orangeduck/Motion…
Supertrack: train a ragdoll to balance and play hours of difficult mocap by gradient descent on smooth/learned/differentiable physics. This changes everything.
Excited to share our latest work with Levi Fussell @HwTheFrondsFold and Kevin Bergamin @_Quazi_ - SuperTrack: Motion Tracking for Physically Simulated Characters using Supervised Learning. For a quick explanation check out this blog post: (1/4)
montreal.ubisoft.com/en/supe…
Simon Clavet retweeted
.@ZivaDynamics presented a machine learning-based system that converts character head meshes into real-time puppets capable of expressing over 72,000 facial shapes within an hour. The video is a real-time demo running in UE5
80.lv/articles/ziva-dynamics…
#animation #3dart #gamedev
I really can't tell if this is real or fake. That's a milestone.
Finishing up this quick project with a short animation test. Kept the rig simple and only with controls I needed for this test
#portraiture #blackbeauty #digitalart #blackpower #portrait #lighting #digitalhuman #animationtest
Simon Clavet retweeted
Another article - this time on joint limits, and how we can automatically compute them from data.
theorangeduck.com/page/joint…
I've also added interactive web demos for this article and my previous article on code vs data driven displacement - much more fun to play with!
This blog post is an important contribution. Go read it.
Another blog post on animation programming fundamentals, and today it's a big one - code vs data driven displacement - or how we can move a character around a game world in a way which is both responsive and realistic.
theorangeduck.com/page/code-…
Simon Clavet retweeted
Turns out I just live coded a simple motion matching setup. Trying to keep it extensible but still cache friendly. youtube.com/watch?v=jcpIrw38…
In this talk, @anorangeduck and @_Quazi_ show our motion-matched physically simulated character to the robots crowd. The grand unification of robotics and game anim is approching...
In case you missed it, here is the talk me and @_Quazi_ gave at the ICRA legged robot workshop: youtube.com/watch?v=W7_z2c2Q…
Train for the high-level objective, while fooling an adversarial discriminator trained on recognizing mocap. Beautiful.
Our paper on adversarial motion priors has been accepted into @siggraph 2021! Adversarial imitation learning is finally starting to work for complex simulated characters.
Paper + code: xbpeng.github.io/projects/AM…
Thanks to my collaborators: Ze Ma, @pabbeel @svlevine @akanazawa
Simon Clavet retweeted
I made a wave based light simulation that runs in real time in a browser. Models effects like dispersion, diffraction, redshift/blueshift, and beam divergence!
quazikb.github.io/WaveEq/ind…
Simon Clavet retweeted
It's pretty awesome how dancing makes robots less intimidating. Looking forward to seeing more nontrivial Machine Learning on these robots. Credit: Boston Dynamics.
This neural network generates human motion between sparse keyframes. Very sparse, actually. A keyframe per second sparse.
This Post is from an account that no longer exists. Learn more
Simon Clavet retweeted
Happy to announce our new SIGGRAPH paper this year - Learned Motion Matching. We use Machine Learning to vastly reduce the memory usage of Motion Matching - allowing it to scale to huge databases of animation. Check out the blog post for more info: montreal.ubisoft.com/en/intr…
Simon Clavet retweeted
Our new #ECCV2020 paper uses learned foot contact estimation and trajectory optimization to reconstruct physically-plausible 3D human motion from video. Check it out!
Paper: arxiv.org/abs/2007.11678
Video: youtu.be/qR9KW6JzXX4
Project: geometry.stanford.edu/projec…
Simon Clavet retweeted
The Eyes Have It: An Integrated Eye and Face Model for Photorealistic Facial Animation youtube.com/watch?v=E3spq4pS…
Atlas jumps on unplanned boxes, using computer vision, and selecting from a library of moves interactively. pscp.tv/RoboticsSeminar/1YqK…
