Michael J. Black
@michael-j-black.bsky.social
Director, Max Planck Institute for Intelligent Systems; Chief Scientist Meshcapade; Speaker, Cyber Valley.
Building 3D humans.
https://ps.is.mpg.de/person/black
https://meshcapade.com/
https://scholar.google.com/citations?user=6NjbexEAAAAJ&hl=en&oi=ao
Building 3D humans.
https://ps.is.mpg.de/person/black
https://meshcapade.com/
https://scholar.google.com/citations?user=6NjbexEAAAAJ&hl=en&oi=ao
Here are all the CVPR projects that I’m part of in one thread.
Conference papers:
PromptHMR: Promptable Human Mesh Recovery
yufu-wang.github.io/phmr-page/
DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models
radualexandru.github.io/difflocks/
Conference papers:
PromptHMR: Promptable Human Mesh Recovery
yufu-wang.github.io/phmr-page/
DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models
radualexandru.github.io/difflocks/
June 9, 2025 at 8:05 AM
Here are all the CVPR projects that I’m part of in one thread.
Conference papers:
PromptHMR: Promptable Human Mesh Recovery
yufu-wang.github.io/phmr-page/
DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models
radualexandru.github.io/difflocks/
Conference papers:
PromptHMR: Promptable Human Mesh Recovery
yufu-wang.github.io/phmr-page/
DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models
radualexandru.github.io/difflocks/
My dream has been to take a photo of a person and extract the 2D sewing pattern of their clothing and then turn it into a 3D garment. ChatGarment does exactly this plus it lets you edit the garment, or create a completely new one, using text prompts. chatgarment.github.io At CVPR2025!
May 28, 2025 at 9:33 AM
My dream has been to take a photo of a person and extract the 2D sewing pattern of their clothing and then turn it into a 3D garment. ChatGarment does exactly this plus it lets you edit the garment, or create a completely new one, using text prompts. chatgarment.github.io At CVPR2025!
To estimate 3D humans from video in world coordinates we add side information to prompt the process. Prompts include bounding boxes, face detections, segmentation masks, and text descriptions. It's currently the most accurate video-based method out there. See us at CVPR2025.
Next in our #CVPR2025 lineup: PromptHMR 👀💫
Turn any video into precise 3D people: occlusions, crowds, world coords solved. State of the art accuracy. 💯
Artists, devs, researchers get instant digital bodies.
Visit our booth 1333 @ CVPR to learn more about PromptHMR!
#AI #3D #DigitalHumans
Turn any video into precise 3D people: occlusions, crowds, world coords solved. State of the art accuracy. 💯
Artists, devs, researchers get instant digital bodies.
Visit our booth 1333 @ CVPR to learn more about PromptHMR!
#AI #3D #DigitalHumans
May 23, 2025 at 3:42 PM
To estimate 3D humans from video in world coordinates we add side information to prompt the process. Prompts include bounding boxes, face detections, segmentation masks, and text descriptions. It's currently the most accurate video-based method out there. See us at CVPR2025.
Check out DiffLocks, appearing at #CVPR2025. From a single image, we estimate about 100K hair strands that you can then physically simulate. We use a dataset of 40K synthetic hair images with ground truth strands. It's all available for research purposes.
Meet DiffLocks, one of our CVPR papers: 3D hair from one image or video, instant mesh, AND public 40,000 3D hairstyle dataset!
Learn more about it at our booth 1333 @ #CVPR2025!
Paper link + author names in thread.
#3DBody #SMPL #MachineLearning #HairTech #GenerativeAI @cvprconference.bsky.social
Learn more about it at our booth 1333 @ #CVPR2025!
Paper link + author names in thread.
#3DBody #SMPL #MachineLearning #HairTech #GenerativeAI @cvprconference.bsky.social
May 20, 2025 at 1:09 PM
Check out DiffLocks, appearing at #CVPR2025. From a single image, we estimate about 100K hair strands that you can then physically simulate. We use a dataset of 40K synthetic hair images with ground truth strands. It's all available for research purposes.
Reposted by Michael J. Black
Yay, @cvprconference.bsky.social, we’re in! 🎉#CVPR2025
5 papers accepted, 5 going live 🚀
Catch PromptHMR, DiffLocks, ChatHuman, ChatGarment & PICO at Booth 1333, June 11–15.
Details about the papers in the thread! 👇
#3DBody #SMPL #GenerativeAI #MachineLearning
5 papers accepted, 5 going live 🚀
Catch PromptHMR, DiffLocks, ChatHuman, ChatGarment & PICO at Booth 1333, June 11–15.
Details about the papers in the thread! 👇
#3DBody #SMPL #GenerativeAI #MachineLearning
May 15, 2025 at 12:49 PM
Yay, @cvprconference.bsky.social, we’re in! 🎉#CVPR2025
5 papers accepted, 5 going live 🚀
Catch PromptHMR, DiffLocks, ChatHuman, ChatGarment & PICO at Booth 1333, June 11–15.
Details about the papers in the thread! 👇
#3DBody #SMPL #GenerativeAI #MachineLearning
5 papers accepted, 5 going live 🚀
Catch PromptHMR, DiffLocks, ChatHuman, ChatGarment & PICO at Booth 1333, June 11–15.
Details about the papers in the thread! 👇
#3DBody #SMPL #GenerativeAI #MachineLearning
Improved foot-ground contact coming soon to MoCapade3.0.
@meshcapade.com incorporará una mejora en su precisión con FootLock. Acá hice un test comparándolo con la captura de mi traje .
#mocapsuit #mocapvideo #3danimation
#mocapsuit #mocapvideo #3danimation
May 8, 2025 at 6:38 AM
Improved foot-ground contact coming soon to MoCapade3.0.
Reposted by Michael J. Black
🎬 Join Meshcapade at FMX!
See how to turn video or text into ready-to-use 3D motion—no suits or markers needed.
Workshop: May 8, 10:00 AM.
Perfect for animation, VFX & game dev!
📍 Info: fmx.de/en/program/p...
#FMX2025 #3DMotion
See how to turn video or text into ready-to-use 3D motion—no suits or markers needed.
Workshop: May 8, 10:00 AM.
Perfect for animation, VFX & game dev!
📍 Info: fmx.de/en/program/p...
#FMX2025 #3DMotion
April 28, 2025 at 9:20 AM
🎬 Join Meshcapade at FMX!
See how to turn video or text into ready-to-use 3D motion—no suits or markers needed.
Workshop: May 8, 10:00 AM.
Perfect for animation, VFX & game dev!
📍 Info: fmx.de/en/program/p...
#FMX2025 #3DMotion
See how to turn video or text into ready-to-use 3D motion—no suits or markers needed.
Workshop: May 8, 10:00 AM.
Perfect for animation, VFX & game dev!
📍 Info: fmx.de/en/program/p...
#FMX2025 #3DMotion
Reposted by Michael J. Black
St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
Haiwen Feng, @junyi42.bsky.social, @qianqianwang.bsky.social, Yufei Ye, Pengcheng Yu, @michael-j-black.bsky.social, Trevor Darrell, @akanazawa.bsky.social
DUSt3R-like framework
arxiv.org/abs/2504.13152
Haiwen Feng, @junyi42.bsky.social, @qianqianwang.bsky.social, Yufei Ye, Pengcheng Yu, @michael-j-black.bsky.social, Trevor Darrell, @akanazawa.bsky.social
DUSt3R-like framework
arxiv.org/abs/2504.13152
April 18, 2025 at 1:06 PM
St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
Haiwen Feng, @junyi42.bsky.social, @qianqianwang.bsky.social, Yufei Ye, Pengcheng Yu, @michael-j-black.bsky.social, Trevor Darrell, @akanazawa.bsky.social
DUSt3R-like framework
arxiv.org/abs/2504.13152
Haiwen Feng, @junyi42.bsky.social, @qianqianwang.bsky.social, Yufei Ye, Pengcheng Yu, @michael-j-black.bsky.social, Trevor Darrell, @akanazawa.bsky.social
DUSt3R-like framework
arxiv.org/abs/2504.13152
Reposted by Michael J. Black
Missed us at GDC?
Watch Part 1 of our talk here 👉 youtu.be/0jCTiQMutow
🚶 Motion capture with MoCapade
🎮 Import directly into Unreal Engine
🎭 Retarget to any character
👀 Bonus: sneak peek at 3D hair & realtime single-cam mocap
🕴️ No suits. 📍 No markers. 🤳 Just one camera.
Watch Part 1 of our talk here 👉 youtu.be/0jCTiQMutow
🚶 Motion capture with MoCapade
🎮 Import directly into Unreal Engine
🎭 Retarget to any character
👀 Bonus: sneak peek at 3D hair & realtime single-cam mocap
🕴️ No suits. 📍 No markers. 🤳 Just one camera.
Meshcapade: From zero to game-ready assets in seconds (GDC 2025 Presentation)
YouTube video by Meshcapade
youtu.be
April 18, 2025 at 12:06 PM
Missed us at GDC?
Watch Part 1 of our talk here 👉 youtu.be/0jCTiQMutow
🚶 Motion capture with MoCapade
🎮 Import directly into Unreal Engine
🎭 Retarget to any character
👀 Bonus: sneak peek at 3D hair & realtime single-cam mocap
🕴️ No suits. 📍 No markers. 🤳 Just one camera.
Watch Part 1 of our talk here 👉 youtu.be/0jCTiQMutow
🚶 Motion capture with MoCapade
🎮 Import directly into Unreal Engine
🎭 Retarget to any character
👀 Bonus: sneak peek at 3D hair & realtime single-cam mocap
🕴️ No suits. 📍 No markers. 🤳 Just one camera.
Will there be an AI tariff? TL;DR: The societies that will "win" the AI race will not be those that develop the technology first. It will be those that are best able to manage the long-term social disruption AI will cause.
perceiving-systems.blog/en/news/what...
on Medium
medium.com/@black_51980...
perceiving-systems.blog/en/news/what...
on Medium
medium.com/@black_51980...
The AI tariff?
perceiving-systems.blog
April 11, 2025 at 12:53 PM
Will there be an AI tariff? TL;DR: The societies that will "win" the AI race will not be those that develop the technology first. It will be those that are best able to manage the long-term social disruption AI will cause.
perceiving-systems.blog/en/news/what...
on Medium
medium.com/@black_51980...
perceiving-systems.blog/en/news/what...
on Medium
medium.com/@black_51980...
Reposted by Michael J. Black
One shot. One town. Endless dancing. 🕺💃🎶
This one-take Unreal animation uses Meshcapade to bring every character to life. No mocap suits, just seamless motion from start to finish.
Stylized, cinematic, and full of vibes; exactly how digital animation should feel 📹✨
#3DAnimation #MarkerlessMocap
This one-take Unreal animation uses Meshcapade to bring every character to life. No mocap suits, just seamless motion from start to finish.
Stylized, cinematic, and full of vibes; exactly how digital animation should feel 📹✨
#3DAnimation #MarkerlessMocap
March 28, 2025 at 2:23 PM
One shot. One town. Endless dancing. 🕺💃🎶
This one-take Unreal animation uses Meshcapade to bring every character to life. No mocap suits, just seamless motion from start to finish.
Stylized, cinematic, and full of vibes; exactly how digital animation should feel 📹✨
#3DAnimation #MarkerlessMocap
This one-take Unreal animation uses Meshcapade to bring every character to life. No mocap suits, just seamless motion from start to finish.
Stylized, cinematic, and full of vibes; exactly how digital animation should feel 📹✨
#3DAnimation #MarkerlessMocap
The arXiv paper for PRIMAL is now online. It's a data-driven, interactive avatar, that can be controlled by varied commands, runs in a game engine, and is responsive to perturbations (without physics simulation). arxiv.org/abs/2503.17544
March 25, 2025 at 10:38 AM
The arXiv paper for PRIMAL is now online. It's a data-driven, interactive avatar, that can be controlled by varied commands, runs in a game engine, and is responsive to perturbations (without physics simulation). arxiv.org/abs/2503.17544
Reposted by Michael J. Black
👨🎤 Ever seen an Interactive Generative avatar running inside @unrealengine.bsky.social?
Check out our latest work, PRIMAL, in collaboration with Max Planck Institute for Intelligent Systems & Stanford University - live demo at @officialgdc.bsky.social! 🎮
www.youtube.com/watch?v=-Gcp...
Check out our latest work, PRIMAL, in collaboration with Max Planck Institute for Intelligent Systems & Stanford University - live demo at @officialgdc.bsky.social! 🎮
www.youtube.com/watch?v=-Gcp...
PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning
YouTube video by Yan Zhang
www.youtube.com
March 21, 2025 at 9:17 PM
👨🎤 Ever seen an Interactive Generative avatar running inside @unrealengine.bsky.social?
Check out our latest work, PRIMAL, in collaboration with Max Planck Institute for Intelligent Systems & Stanford University - live demo at @officialgdc.bsky.social! 🎮
www.youtube.com/watch?v=-Gcp...
Check out our latest work, PRIMAL, in collaboration with Max Planck Institute for Intelligent Systems & Stanford University - live demo at @officialgdc.bsky.social! 🎮
www.youtube.com/watch?v=-Gcp...
Reposted by Michael J. Black
🎉🎉🎉 Happy to announce that the code for our paper Gaussian Garments is now public!
Link: github.com/eth-ait/Gaus...
Gaussian Garments uses a combination of 3D meshes and Gaussian splatting to reconstruct photorealistic simulation-ready digital garments from multi-view videos. 🧵
Link: github.com/eth-ait/Gaus...
Gaussian Garments uses a combination of 3D meshes and Gaussian splatting to reconstruct photorealistic simulation-ready digital garments from multi-view videos. 🧵
March 20, 2025 at 3:46 PM
🎉🎉🎉 Happy to announce that the code for our paper Gaussian Garments is now public!
Link: github.com/eth-ait/Gaus...
Gaussian Garments uses a combination of 3D meshes and Gaussian splatting to reconstruct photorealistic simulation-ready digital garments from multi-view videos. 🧵
Link: github.com/eth-ait/Gaus...
Gaussian Garments uses a combination of 3D meshes and Gaussian splatting to reconstruct photorealistic simulation-ready digital garments from multi-view videos. 🧵
The CameraHMR video is now on Youtube. This is currently the most accurate single-image method for estimating 3D human shape and pose. The paper will be presented at 3DV. The code and data are all on-line here: camerahmr.is.tue.mpg.de
youtu.be/v3WzpjXpknc
youtu.be/v3WzpjXpknc
CameraHMR: Aligning People with Perspective (3DV 2025)
YouTube video by Michael Black
youtu.be
March 17, 2025 at 2:10 PM
The CameraHMR video is now on Youtube. This is currently the most accurate single-image method for estimating 3D human shape and pose. The paper will be presented at 3DV. The code and data are all on-line here: camerahmr.is.tue.mpg.de
youtu.be/v3WzpjXpknc
youtu.be/v3WzpjXpknc
Reposted by Michael J. Black
🎮 Motion Generation in Unreal, made SMPL.
Experience real-time reactive behavior—characters adapt instantly to your input. With controllable generative 3D motion, every move is unique. Real-time motion blending keeps it smooth.
🚀 See it at Booth C1821!
#3DAnimation #MotionGeneration #GameDev #GDC
Experience real-time reactive behavior—characters adapt instantly to your input. With controllable generative 3D motion, every move is unique. Real-time motion blending keeps it smooth.
🚀 See it at Booth C1821!
#3DAnimation #MotionGeneration #GameDev #GDC
March 13, 2025 at 11:03 AM
🎮 Motion Generation in Unreal, made SMPL.
Experience real-time reactive behavior—characters adapt instantly to your input. With controllable generative 3D motion, every move is unique. Real-time motion blending keeps it smooth.
🚀 See it at Booth C1821!
#3DAnimation #MotionGeneration #GameDev #GDC
Experience real-time reactive behavior—characters adapt instantly to your input. With controllable generative 3D motion, every move is unique. Real-time motion blending keeps it smooth.
🚀 See it at Booth C1821!
#3DAnimation #MotionGeneration #GameDev #GDC
And it just keeps coming from @meshcapade.com -- next up, real-time markerless motion capture from a single camera. Check it out at #GDC2025. Yes, the founders will be there to dance for you (as in this video) but it's more fun to try it yourself!
🎥✨ One camera. Live motion. Zero hassle.
Stream real-time motion to 3D characters in Unreal—no suits, no markers, just seamless animation. See it LIVE at Booth C1821!
#GDC2025 #MotionCapture #Realtime
Stream real-time motion to 3D characters in Unreal—no suits, no markers, just seamless animation. See it LIVE at Booth C1821!
#GDC2025 #MotionCapture #Realtime
March 5, 2025 at 10:47 AM
And it just keeps coming from @meshcapade.com -- next up, real-time markerless motion capture from a single camera. Check it out at #GDC2025. Yes, the founders will be there to dance for you (as in this video) but it's more fun to try it yourself!
Reposted by Michael J. Black
Faces, Expressions, Hair—Brought to Life with Meshcapade.
From facial animation to 3D hair, creating digital humans has never been easier.
See it at #GDC2025! Visit Booth C1821 and experience motion, detail, expression.
#UnrealEngine #3DAnimation #MotionCapture #FacialAnimation #genAI #Meshcapade
From facial animation to 3D hair, creating digital humans has never been easier.
See it at #GDC2025! Visit Booth C1821 and experience motion, detail, expression.
#UnrealEngine #3DAnimation #MotionCapture #FacialAnimation #genAI #Meshcapade
March 3, 2025 at 9:00 AM
Faces, Expressions, Hair—Brought to Life with Meshcapade.
From facial animation to 3D hair, creating digital humans has never been easier.
See it at #GDC2025! Visit Booth C1821 and experience motion, detail, expression.
#UnrealEngine #3DAnimation #MotionCapture #FacialAnimation #genAI #Meshcapade
From facial animation to 3D hair, creating digital humans has never been easier.
See it at #GDC2025! Visit Booth C1821 and experience motion, detail, expression.
#UnrealEngine #3DAnimation #MotionCapture #FacialAnimation #genAI #Meshcapade
I'll be at #GDC2025 so if you are there and want to meet, you can probably find me at the @meshcapade.com booth.
We're excited to announce that we are going to the #GDC2025!
See our demos & Unreal Engine plugin in action—live!
We’re bringing next-gen markerless motion capture to game dev.
Come experience it for yourself—can't wait to see you all at GDC 2025!
#GameDevelopment #UnrealEngine #MotionCapture #GDC
See our demos & Unreal Engine plugin in action—live!
We’re bringing next-gen markerless motion capture to game dev.
Come experience it for yourself—can't wait to see you all at GDC 2025!
#GameDevelopment #UnrealEngine #MotionCapture #GDC
February 19, 2025 at 1:53 PM
I'll be at #GDC2025 so if you are there and want to meet, you can probably find me at the @meshcapade.com booth.
Reposted by Michael J. Black
Meshcapade was just featured again in DER SPIEGEL and their Spiegel-Shortcut podcast! 🎙️✨
The podcast highlights the diversity of ideas shaping the future - something we’re very proud to part of!
▶️ Watch on Youtube: www.youtube.com/watch?v=gN0X...
The podcast highlights the diversity of ideas shaping the future - something we’re very proud to part of!
▶️ Watch on Youtube: www.youtube.com/watch?v=gN0X...
KI-Innovation: Hat Deutschland Antworten auf ChatGPT, DeepSeek & Co.? – Shortcut | DER SPIEGEL
YouTube video by DER SPIEGEL
www.youtube.com
February 11, 2025 at 7:13 PM
Meshcapade was just featured again in DER SPIEGEL and their Spiegel-Shortcut podcast! 🎙️✨
The podcast highlights the diversity of ideas shaping the future - something we’re very proud to part of!
▶️ Watch on Youtube: www.youtube.com/watch?v=gN0X...
The podcast highlights the diversity of ideas shaping the future - something we’re very proud to part of!
▶️ Watch on Youtube: www.youtube.com/watch?v=gN0X...
Turning videos into 3D humans has never been easier or more accurate. MoCapade 3.0 improves everything over 2.0 while adding 3D camera tracking (and output) and multi-person capture. Try out the new state-of-the-art. Of course, there's more to come.
February 6, 2025 at 6:32 AM
Turning videos into 3D humans has never been easier or more accurate. MoCapade 3.0 improves everything over 2.0 while adding 3D camera tracking (and output) and multi-person capture. Try out the new state-of-the-art. Of course, there's more to come.
Reposted by Michael J. Black
MoCapade 3.0 goes LIVE today 🥳 🎉
👯 Multi-person capture
🎥 3D camera motion
🙌 Detailed hands & gestures
⏫ New GLB, MP4 and SMPL export formats
All from a single camera. Any camera! 📹 🤳 📸
Ready, set, CAPTURE! 🏂
youtu.be/jizULlZTAR8
👯 Multi-person capture
🎥 3D camera motion
🙌 Detailed hands & gestures
⏫ New GLB, MP4 and SMPL export formats
All from a single camera. Any camera! 📹 🤳 📸
Ready, set, CAPTURE! 🏂
youtu.be/jizULlZTAR8
MoCapade 3.0: Meshcapade's markerless mocap is live 🥳 🎉
YouTube video by Meshcapade
youtu.be
February 5, 2025 at 4:00 PM
MoCapade 3.0 goes LIVE today 🥳 🎉
👯 Multi-person capture
🎥 3D camera motion
🙌 Detailed hands & gestures
⏫ New GLB, MP4 and SMPL export formats
All from a single camera. Any camera! 📹 🤳 📸
Ready, set, CAPTURE! 🏂
youtu.be/jizULlZTAR8
👯 Multi-person capture
🎥 3D camera motion
🙌 Detailed hands & gestures
⏫ New GLB, MP4 and SMPL export formats
All from a single camera. Any camera! 📹 🤳 📸
Ready, set, CAPTURE! 🏂
youtu.be/jizULlZTAR8
Reposted by Michael J. Black
"AI is like electricity: the decisive factor is not who invented it, but who knows how to use it best." ⚡
A fantastic article from @spiegel.de about the importance of the AI technologies we're building at Meshcapade & the wider German AI startup space, including groundbreaking work from startups like OSORA medical, EndoSurge, Mirelo AI, Maddox AI, Polybot.
www.spiegel.de/wissenschaft...
www.spiegel.de/wissenschaft...
(S+) Künstliche Intelligenz: In Deutschland entsteht eine innovative KI-Szene
Künstliche Intelligenz erobert die Welt: Start-ups in Württemberg versuchen, auf dem Weltmarkt mitzumischen. Sie entwickeln ferngesteuerte Herzkatheter, KI-generierte Filmmusik und Agrarroboter.
www.spiegel.de
January 28, 2025 at 11:30 AM
"AI is like electricity: the decisive factor is not who invented it, but who knows how to use it best." ⚡