More demos and code available at intelligentsensingandrehabilitation.github.io/MonocularBio...

JD did a great job creating a Gradio demo so try it out and let us know what you think

And here is a video of JD going on a celebratory run that the preprint is out :)

The next paper is BiomechGPT arxiv.org/abs/2505.18465 with @antihebbiann.bsky.social and Ruize Yang which trains a language model to be fluent in tokenized movement sequences. This draws inspiration from MotionGPT but focuses on benchmarking performance on clinically meaingful tasks.

Here is another example. It also captures some imperfections like little foot slips we want to improve.

Since then, we've tuned it up to handle anthropomorphic and muscle scaling. Still lots of work to do further tuning this as there are many things we aren't scaling such as mass and inertia and optimizing w.r.t. the EMG data we have from our wearable sensors.

We already do, although currently just for the bilevel scaling and marker offsets that we optimize jointly with the inverse kinematics (arxiv.org/abs/2402.17192)

Starting to think about scaling for muscles, which we need for some of our new stuff to get rid of the scaling inconsistency.

Another fun one. In realtime (instead of the 60 fps -> 30 fps in the prior)

Super stoked about the progress @jdpeiffer.bsky.social is making on monocular biomechanical analysis. Also really fun to connect back to my old drone hobby (and they are so much easier now than a decade ago buildandcrash.blogspot.com/2014/10/refl...)