🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Oh! Delighted to see our Panoptic Studio data contributing to various research directions! It's also fun spotting the younger version of myself and Tomas in the videos.

I will be giving a talk (remotely) at the #RSS24 workshop on Dexterous Manipulation today. I will be talking about our lab's effort in scaling up human motion datasets across various in-the-wild and HOI situations. If you are attending RSS, please visit the workshop!

💡 Our workshop was full of 'aha!' moments 👏 Shoutout to our awesome speakers. Sammy Joe Christen, Matei, @kevindoherty95, @tesshel, Tess, Hanbyul (Han) Joo, Robert Katzschmann, Jitendra, He Wang, and awesome spotlight authors. 🍿Missed it? Catch the replays here:t.ly/qVjLu

🚨ECCV 2024 Paper Alert 🚨 ➡️Paper Title: Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models 🌟Few pointers from the paper 🎯Understanding the inherent human knowledge in interacting with a given environment (e.g.,

The full version of our ParaHome DB has been released. Our DB offers 3D body, hand, and object movements, paired with text annotations for the actions. Huge kudos to our amazing team for their incredible hard work.

It has been a great experience working with the organizing team for this workshop! We welcome your participation at #ECCV2024! 🇮🇹 Fellow organizers: Evonne Ng, Fiona Ryan, Sangmin Lee, Paul Liang, Gül Varol, Shiry Ginosar, Hanbyul (Han) Joo, Justine Cassell, James Matthew Rehg, LP Morency

Join us for our Artificial Social Intelligence Workshop at #ECCV2024! Check out the full program and our amazing lineup of speakers!

Personalized 3D Generative Avatars from a Single Portrait Contributions: 1. Generate a personalized 3D avatar from a reference portrait image with controllable facial attributes. 2. Create high-quality synthetic 2D video datasets with diverse attribute editing from a reference

PERSE Personalized 3D Generative Avatars from A Single Portrait

We will present our PERSE at #CVPR2025 Creating 3D personalized generative avatars from a single image is a tough challenge, and I’m incredibly proud of my students, Hyunsoo Cha and Inhee Lee, for their amazing efforts. Code will be released soon: hyunsoocha.github.io/perse/

We will present ParaHome at #CVPR2025! We're deeply grateful for the insightful feedback from reviewers on our previous submissions, which helped us refine and improve our work in many ways. Huge thanks to our team. Amazing that just three junior grad students built everything.

We will be hosting the workshop on "Agents in Interactions, from Humans to Robots" at CVPR2025 #CVPR2025 , welcome to join us by submitting a paper or stopping by our talks/posters! For more info please check out: agents-in-interactions.github.io

The 2nd 3D HUMANS workshop is back at #CVPR2025! 📍Join us on June 12 afternoon in Nashville for a 2025 perspective on 3D human perception, reconstruction & synthesis. 🖼️ Got a CVPR paper on 3D humans? Nominate it to be featured in our poster session! 👉 tinyurl.com/3d-humans-2025

I'm attending ICRA this week to explore exciting robotics research! I'll also be giving a talk at the Wearable Robotics Workshop, where I'll share our lab's recent efforts to bridge human motion estimation with robot learning. Hope to see you there! sites.google.com/andrew.cmu.edu…

Join us for our workshop: Agents in Interaction, from Humans to Robots, on June 12th at 9:25 am, Room 213! We have an exciting line of speakers from both robotics and digital humans. Please come! #CVPR2025 More info: agents-in-interactions.github.io

How have we progressed in understanding 3D humans, from reconstruction to synthesis? 👉#CVPR2025 3D Humans workshop! 🕑13:50, June 12 📍Room 110B 👉Exciting talks by Angjoo Kanazawa, Michael Black, Gerard Pons-Moll, Sebastian Starke, Hanbyul (Han) Joo, + panel discussion w. Georgios Pavlakos!

Today! Please come to see our poster session at #CVPR2025 to learn more about our personalized generative 3D face model, PERSE!