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=aohttps://bsky.app/profile/michael-j-black.bsky.socialhttps://bsky.app/profile/michael-j-black.bsky.social/post/3lr5w6wnv5k2qHere 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/09 Jun 2025 08:05 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lr5w6wnv5k2qhttps://bsky.app/profile/michael-j-black.bsky.social/post/3lq7vj7edtk2cMy 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! [contains quote post or other embedded content]28 May 2025 09:33 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lq7vj7edtk2chttps://bsky.app/profile/michael-j-black.bsky.social/post/3lptxtxg35227To 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. [contains quote post or other embedded content]23 May 2025 15:42 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lptxtxg35227https://bsky.app/profile/michael-j-black.bsky.social/post/3lpm5vhphbs24Check 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. [contains quote post or other embedded content]20 May 2025 13:09 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lpm5vhphbs24https://bsky.app/profile/michael-j-black.bsky.social/post/3lonch5bbbk23Improved foot-ground contact coming soon to MoCapade3.0. [contains quote post or other embedded content]08 May 2025 06:38 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lonch5bbbk23https://bsky.app/profile/michael-j-black.bsky.social/post/3lmk2spaots2oWill 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. https://perceiving-systems.blog/en/news/what-will-be-the-tariff-on-ai on Medium https://medium.com/@black_51980/the-ai-tariff-7c349b82591611 Apr 2025 12:53 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lmk2spaots2ohttps://bsky.app/profile/michael-j-black.bsky.social/post/3ll73dpr3q22uThe 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 [contains quote post or other embedded content]25 Mar 2025 10:38 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3ll73dpr3q22uhttps://bsky.app/profile/michael-j-black.bsky.social/post/3lkldgmszh22bThe 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 https://youtu.be/v3WzpjXpknc17 Mar 2025 14:10 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lkldgmszh22bhttps://bsky.app/profile/michael-j-black.bsky.social/post/3ljmsjdnims2aAnd 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! [contains quote post or other embedded content]05 Mar 2025 10:47 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3ljmsjdnims2ahttps://bsky.app/profile/michael-j-black.bsky.social/post/3lijwf7qa5c2bI'll be at #GDC2025 so if you are there and want to meet, you can probably find me at the @meshcapade.com booth. [contains quote post or other embedded content]19 Feb 2025 13:53 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lijwf7qa5c2bhttps://bsky.app/profile/michael-j-black.bsky.social/post/3lhiho7yqa224Turning 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. [contains quote post or other embedded content]06 Feb 2025 06:32 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lhiho7yqa224https://bsky.app/profile/michael-j-black.bsky.social/post/3lgalmx5gns24Code and data are now online for CameraHMR, our state-of-the-art parametric 3D human pose and shape (HPS) estimation method that will appear at hashtag#3DV2025. https://github.com/pixelite1201/CameraHMR/21 Jan 2025 09:56 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lgalmx5gns24https://bsky.app/profile/michael-j-black.bsky.social/post/3lfys3lctwk2uHow can LLMs help computers see, how human motion is the dark matter of computer vision, what's artificial good-enough intelligence, & more? With Ben Kaplan at Deep Venture Partners. @meshcapade.com @mpi-is.bsky.social APPLE: lnkd.in/ez8cKuNs SPOTIFY: lnkd.in/eWtmtHd5 https://lnkd.in/ez8cKuNs18 Jan 2025 07:31 +0000at://did:plc:5oaefyb2fa6bk7cfjry6jiop/app.bsky.feed.post/3lfys3lctwk2u