Silvia Zuffi

Research scientist at IMATI-CNR, affiliated researcher at MPI-IS. Modeling 3D animals for 3D reconstruction.

[Silvia Zuffi @silvia_zuffi]

A huge thanks to @AouadaDjamila for organizing @Euvip2026 and having me along with the amazing @dimadamen, @eliricci_ and @ftm_guney as kenote speakers!

[Silvia Zuffi @silvia_zuffi]

@sha2nk_t I want it for Italy too!

[Silvia Zuffi @silvia_zuffi]

@eerac @theworldlabs I can definitely picture the excitement! Congratuations!

[Silvia Zuffi @silvia_zuffi]

@eerac @drfeifei congratulations!

[Silvia Zuffi @silvia_zuffi]

🚀 Code release!

The code for SAM3D Animal is now available!

🐾 Estimates the 3D shape and pose of multiple animals from a single image
🐾 Supports multiple species with the SMAL+ parametric animal model
Project page :
https://t.co/WdNof7YoBh

Congratulations @GeorgeHu240266

[Silvia Zuffi @silvia_zuffi]

wow, congratulations to the team!

[Michael Black @Michael_J_Black]

The MetaHuman Animator Markerless Motion Capture (MCC) Plugin is now live in Unreal Engine 5.8. It takes a video and captures the 3D motion of the body, face, and hands. You can download it for free from https://t.co/O8mM4yspyF:

https://t.co/hVAx2Ti66I

This release is a dream come true and I’m grateful to Epic Games for believing in the technology and the Meshcapade team.

We joined Epic just a few months ago and have completely rearchitected our approach. The model is now based on a diffusion transformer, which helps it deal with occlusion. Meshcapade’s MoCapade solution was already best in class, and we’ve made it even better.

Based on our testing, this is the most accurate markerless mocap solution ever made. Body pose is 9% more accurate, the motions are 29% smoother, and foot sliding is reduced by 34%, all while retaining the same high accuracy in 3D world motion.

The MetaHuman team has turned this technology into a full-fledged tool for animators that gives them complete creative control of their animation from conception through to the final cut. With any camera, you can capture your own motion and get it onto your character.

No special clothes.
No special background.
No special camera.
No need to calibrate.
Any length video.

All processing is done locally — your data never leaves your machine. Use the output to animate Metahumans or retarget to other characters. You can even get SMPL-X out if you want.

Limitations? The current version only works with a static camera and one person and is currently only tested and supported on Windows. But this is just the beginning!

[Michael Black @Michael_J_Black]

Big news: @Meshcapade is now part of Epic Games. This is a perfect match for our technology and team and I am super excited about what we will build together.

I want to thank our many supporters who have provided funding and/or advice on our journey from 2018 to today, including @MP_Innovation, @maxplanckpress, @MPI_IS, @PerceivingSys, @matrixvc, @dcstalder, @dianaberlin, @HV_Capital, Zuzanna Czapinska, LBBW VC, @GoodwaterCap, CLO Virtual Fashion (@itsclo3d), @grbradsk, @lucvincent, @JeffDean, @ballmatthew, Andrew Hamel, Bill O’Farrell, Ammar Zakiullah, @Nicolas_Keller, Alex Diehl, @goodwinlaw, YPOG, @NVIDIA Inception Program, @msft4startups, and many more!

Most importantly, I want to thank my co-founders @naureenmahmood and Talha Zaman and the whole @Meshcapade team. There is nothing more rewarding than working with great people who you like and trust to build products that customers love using technology you believe in. Thank you, thank you, thank you. Now, on to the next phase!

https://t.co/fmMYXfSSoK

[Silvia Zuffi @silvia_zuffi]

@TrackingPlumes Simply FANTASTIC!!!

[Silvia Zuffi @silvia_zuffi]

@sha2nk_t @Michael_J_Black Congratulations Shashank!!

[Silvia Zuffi @silvia_zuffi]

@jampani_varun @arcade_ai Congratulations Varun!

[Naureen Mahmood @naureenmahmood]

We'll be live at @siggraph with our real-time 3D #MotionCapture and #MotionGeneration demos!

Come see us in #Vancouver!

[#ICIAP2025 @iciapconf]

📢 #ICIAP2025 Update! Meta-reviews are now on CMT.

Use the valuable feedback ✍️ to prep your camera-ready version.

Reminder: Each accepted paper requires one full registration.

Register by the June 30 to secure your spot at the early-bird rate! 🗓️

🔗 https://t.co/dWfqZEdv7x

[Michael Black @Michael_J_Black]

Amazing showing for little @Meshcapade at CVPR2025. The big companies may have more papers but I bet none of them have more papers per employee!

Huge steps forward in 3D human pose and shape estimation in world coordinates, 3D hair regression from a single image, an LLM that's an expert on using tools related to 3D humans, an LLM that can infer 3D garments from an image, and a new bar for estimating 3D humans and objects together.

New ideas, code, and datasets. See you in Nashville!

[Meshcapade @meshcapade]

🔥 🔥 🔥 hot off the press! 🤖

[#ICIAP2025 @iciapconf]

⚠️ Last few days to Submit Your Paper for #ICIAP2025!

Time’s running out to share your research in image analysis and computer vision at ICIAP 2025! 🏛️

📆 Deadline: April 15, 2025
🔗 Submit now: https://t.co/63MvSg6LyJ

#DeepLearning #ComputerVision #ImageAnalysis

[#ICIAP2025 @iciapconf]

🚄 Planning your trip to #ICIAP2025 in Rome?

We’ve partnered with Trenitalia to offer participants 15% discounted fares, with flexible change and refund options.

You can book directly through the dedicated platform on our site:
https://t.co/omMwm2lIyM

[#ICIAP2025 @iciapconf]

🚀The second round submission of #ICIAP2025 is open!

Be part of Rome 2025 and share your research on computer vision, pattern recognition and image processing,. Don’t miss this opportunity! 🚀

📆 Deadline: April 15, 2025
🔗 Submit your paper: https://t.co/63MvSg6LyJ

[Elliott / Shangzhe Wu @elliottszwu]

We have extended the submission deadline to PT 23:59 April 4.

Good chances to win free registrations @CVPR!

[Elliott / Shangzhe Wu @elliottszwu]

Submission deadline has been extended by a week to April 4.

Submit your latest 4D work to the workshop @CVPR:
4D Gaussians, point tracking, dynamic SLAMs, egocentric, human motion, multi-modal world models, embodied AI... you name it!

https://t.co/PxAj0kvVCb

[Meshcapade @meshcapade]

Wukong in action, trying out our real-time motion to video livelink demo!

Curious? Come check out our booth C1821 at the #GDC!