JLPM

Code, data and the paper are available on the project website! upc-virvig.github.io/MMVR/ Thanks @SympCompAnim for organizing a great conference! and my colleagues @ClipeCurie and supervisors for all the support :)

To obtain accurate positioning of the hands, we apply inverse kinematics with the hand-held controllers as end effectors

Motion Matching searches over an animation database for the best match for the current avatar pose and the predicted trajectory

A lightweight feedforward neural network predicts the body orientation from the rotation, velocity and angular velocity of all three devices

We propose a new method to animate self-avatars using only one HMD and two hand-held controllers. Our system can be divided into three parts: • Body orientation prediction • Motion Matching • Final pose adjustments

It was great to participate at ACM SIGGRAPH/Eurographics #SCA2022 with our paper "Combining Motion Matching and Orientation Prediction to Animate Avatars for Consumer-Grade VR Devices" We present a method to animate VR avatars with Motion Matching! 🧵 upc-virvig.github.io/MMVR/

ups, copié mal el link: youtu.be/4k4wD7eXEZA

gracias! :D es verdad! se cortó la última letra, este es el bueno: youtu.be/4k4wD7eXEZA

He estado desaparecido desde que acabé el máster :( Estaba fuera de España por trabajo y no he podido dedicarme a YouTube. A ver si me reconecto a las redes sociales poco a poco :D De momento he subido un vídeo de algo que estuve haciendo antes del verano youtu.be/4k4wD7eXEZ