Post
Excited to share my latest preprint with
@oliveiracaio
and
@fabee
: "Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation"! ππΊ
Platypose is our new approach to estimating 3D human motions from 2D observations. What makes it special? π€© Well, we're able to estimate multiple hypotheses for motion, which is pretty cool!
But here's the best part: our model is not only accurate but also well-calibrated. We've made sure that the predicted uncertainty matches the models confidence, so you can have a better understanding of Platypose's predictions.
Project Page: https://sinzlab.org/publications/2024-platypose.html
Paper: Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation (2403.06164)
Model Weights: sinzlab/platypose
The code is open-source, so please leave a star β
https://github.com/sinzlab/platypose
Platypose is our new approach to estimating 3D human motions from 2D observations. What makes it special? π€© Well, we're able to estimate multiple hypotheses for motion, which is pretty cool!
But here's the best part: our model is not only accurate but also well-calibrated. We've made sure that the predicted uncertainty matches the models confidence, so you can have a better understanding of Platypose's predictions.
Project Page: https://sinzlab.org/publications/2024-platypose.html
Paper: Platypose: Calibrated Zero-Shot Multi-Hypothesis 3D Human Motion Estimation (2403.06164)
Model Weights: sinzlab/platypose
The code is open-source, so please leave a star β
https://github.com/sinzlab/platypose
