Meshcapade Announces Advanced Motion Blending Feature

Meshcapade, a tech startup building foundation models to enable 3D digital humans for AI, gaming, VR, fashion and healthcare, recently introduced a new feature in motion blending.

🚨 New awesome feature announcement! 🚨

MOTION BLENDING IS HERE! 🚀✨

Blend any motion from our platform - whether it's from video or text - with seamless, AI-driven transitions. From bold moves to subtle shifts, your animations have never looked smoother!#SMPL #3D… pic.twitter.com/84j7NGNCpM

— Meshcapade (@meshcapade) November 5, 2024

This new feature allows users to blend any motion from the Meshcapade platform—whether sourced from video or text—into seamless, AI-driven transitions. 

Meshcapade states that its mission is to build foundation models that enable digital humans to see, understand, and behave just like real people.

Patented Avatar Technology

Meshcapade’s avatar technology is built on our patented SMPL body model (US patent US10395411B2). SMPL is an entire suite of 3D models for the body, face, hands and feet developed from hundreds of thousands of precise 3D scans.

To attain accuracy, Meshcapade’s SMPL uses machine learning to capture the statistics of 3D body shapes across diverse populations.

“When we started Meshcapade, what drove us all was an ambition, a dream, to solve these perception problems. At our core, we are computer vision scientists. But that enthusiasm very easily expanded into computer graphics, machine learning and AI — all the tools available to us to solve a century-old problem of helping machines understand and interact with the world around them!” writes Naureen Mahmood, CEO & Co-founder @Meshcapade. 

Although based on a highly detailed 3D model of the human body (a "parametric human model"), Meshcapade is flexible enough to apply its motion and animation to other types of characters and skeleton structures.

https://x.com/meshcapade/status/1853855622602899673The inception story of Meshcapade goes back to 2018 in Tübingen by Naureen Mahmood (CEO), Talha Zaman (CTO), and Michael Black (Chief Scientist).