🙌 You asked, we delivered! After last week’s camera extraction demo, many of you wanted to know how to do it yourself. 🎥✨ The key is simple: ➡️ Select Multi-Person (even for single-person videos — that’s where camera extraction works right now) ➡️ Download as .glb Then

I made a new test to compare the motion capture results from my #perceptionneuronstudio suit with those obtained through video capture using @meshcapade Here are the results

Link to PRIMAL Project & Code: https://t.co/wmrOpnt2Mc

Can we build a model with basic functionalities of a human motor system with perpetual motion, which reacts instantly and quickly adapts to interactions and input? 🤔 👉 The answer is PRIMAL (#ICCV2025)! Code and Unreal demo are now online!!  🎉It’s a simple idea: use a

Waterless printing? We’re into it. SHEIN’s digital thermal transfer printing says goodbye to water-heavy dyeing and printing and keeps the prints looking sharp. Learn more at the link.

Any movement, any subject, any environment. 📸 That's the creative freedom of Meshcapade's Markerless MoCapade. 🚀 We deliver the industry's most accurate 3D motion and body shape data from any single video source. Our AI transforms footage—from subtle social gestures to

Happy Halloween from @alerender_mocap! 🎃 Check out his eerie animation! Amazing VFX, camera angles and motions 🔥

The SMPL Body Model Team receiving the Everingham Prize Award

Only 3 in 10 Veterans know about 0% down home loans. Join our mission to help veterans find their way home.

The BEDLAM2.0 dataset (B2) is here, just in time to train your 3D human pose and shape estimation methods for CVPR. B2 goes beyond BEDLAM (B1) to include widely varied and natural camera motions and fields of view, more diverse body shapes, strand-based hair, more garments,

Code and the Unreal Engine demo are already online:

You should be dancing 🎵

It has been such a pleasure seeing the innovations and novel ideas being built on top of #SMPL, and its enduring impact on research & industry over the past decade! Last night, the PAMI committee awarded our work the Mark Everingham Prize at the @ICCVConference🏆

Our very own @cnsdqzyz & @Michael_J_Black presenting PRIMAL at @ICCVConference -- happening NOW! 🦾 Don't miss it!! #256 PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning 👇 see details below

@AdskMaya Watch the tutorial on YouTube:

@AdskMaya 👉 Access the full written tutorial and download the required files here: 🔗 Maya Integration Guide:

🎬 New Tutorial: Retarget Meshcapade Motion in Maya with HumanIK! Learn how to bring Meshcapade motion data into Autodesk Maya — step by step (@AdskMaya). ✅ Prepare your animation and T-pose ✅ Set up HumanIK with our SMPL skeleton ✅ Retarget & bake clean keyframes for your

SMPL is an outcome every researcher dreams of. Congratulations 🎊 @Michael_J_Black & everyone at @meshcapade team for a decade long journey 🙌Not SOTA, success is when you are the default baseline for the whole community

SMPL is 10 years old and has done what we hoped — it changed the way the field estimates and models 3D humans and their motion. I’m delighted that the original team has been recognized today at @ICCVConference with the Mark Everingham Prize. The prize is given to individuals or

We're in Hawaii this week for @ICCVConference! 🌴 Don't miss the chance to come say hi 👋

I’ve been testing with some stunt videos where they perform the ‘dead man’ fall, just to see how it looks in video motion capture. This is one of the tests with @meshcapade @reallusion #iclone8 #unrealengine5 hashtag#mocapvideo hashtag#3danimation

@venturetwins If you actually care about consistency: you could use a combo of meshcapade/metahuman for motion capture, then do video2video on comfy with a model like WAN, as an infra investor you would then realize that shortening inference time is the infra play you should be looking for

Another test ... 🦿 Mocap video : @meshcapade 👩 Character :@reallusion 🎬 Footage video @SofiaStunts #mocapvideo #3danimations