The HuMoGen #CVPR2025 deadline is in 6 days🙀🙀🙀 We invite you to submit your #MOTION papers! More details @ humogen.github.io

Introducing our latest work on multi-party gesture synthesis, accepted in #CVPR2024. We take a step toward controllable gesture synthesis. What's more, we introduce the Dungeons & Dragons (DnD) dataset: 5 participants playing DnD for hours and, well, naturally gesticulating.

[1/2] Excited about your paper being accepted to CVPR? Looking to extend its impact to more movers and shakers in the Human Motion Generation community? 🕺💡 Submit a one-page abstract to the HuMoGen Workshop at #CVPR2024 and reach an even broader audience! 📝✨ #CVPR2025 #HuMoGen

Paper decisions are now available at OpenReview🕺

Coming up tomorrow (Tue) morning🤩🤩🤩 Summit 430 - starting at 8:30 AM

Starting now in Room 430, Summit Building. HuMoGen - CVPR Workshop 2025

🌟 A huge thank you to our incredible speakers, poster presenters, and the enthusiastic audience for making this event a success! 🙏👏 #CVPR2025 #HuMoGen

How can we meta-learn a prior for human radiance and SDF fields to tackle ambiguities in the sparse (few camera) performance capture setting? Check out our #ECCV 2024 work MetaCap! Project page: vcai.mpi-inf.mpg.de/projects/MetaC… Team: Guoxing Sun, Rishabh Dabral, Pascal Fua, Christian

#ECCV2024 Presenting ReMoS, our latest work on Reactive Motion Synthesis for modeling 2-person interactions. Project page: vcai.mpi-inf.mpg.de/projects/remos/ Team: Anindita Ghosh, Rishabh Dabral, Vlad Golyanik, C. Theobalt, P. Slusallek

The full recording of the workshop is now available 📽️📽️📽️ humogen.github.io youtube.com/watch?v=lkQ4sD…

[1/6]🧵: Our project CasperDPM --- A method to augment hands in real time, has been accepted to #SIGGRAPHAsia2024 ! Project Page: yoterel.github.io/casper-project… -->

We're back! 🚶‍♀️🕺 The Human Motion Generation Workshop returns to #CVPR2025 with an amazing lineup of speakers from academia and industry. 🎤✨ 📢 Call for Papers and details: humogen.github.io Daniel Holden Ziwei Liu Yuting Ye, and Taku Komura.

Now hiring: Multiple PhD students to start in fall 2025, for research on combining neural and symbolic/interpretable models of language, vision, and action. Work with world-class advisors at Universität Saarland, MPI Informatics, MPI-SWS, @CISPA ,DFKI. Details: neuroexplicit.org/jobs/

Human Motion people - There is still a path to Nashville...Just saying #CVPR2025

🚀 Check out our #CVPR2025 paper BimArt! 👐🔧 We generate 3D bimanual interactions with articulated objects by: ✅ Predicting contact maps from object trajectories ✅ Using an articulation-aware feature representation Project Webpage: vcai.mpi-inf.mpg.de/projects/bimar… VCAI - MPI for Informatics

One week before the HuMoGen deadline. The submission portal is open at: openreview.net/group?id=thecv…

#CVPR2025 Want to put life into your LLM chatbots with gesticulating characters? Checkout M. Hamza Mughal's work on generating semantically meaningful gestures using RAG with a gesture diffusion model. Congratulations to Hamza and collaborators at VCAI - MPI for Informatics and Neuroexplicit Models of Language, Vision, Action !

Full body tracking from a VR headset? In our #CVPR2025 Highlight paper “FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video”, we show it’s possible using only body-facing cameras. 🧵...

🏃Today at CVPR!!! 📅🕐 13:00–17:00, 📍Room 110B 💃

{1/8} 🧵 When you click a link, have you ever wondered: “Which webpage is actually important?” Google answered that with PageRank—treating the web as a Markov chain. Now imagine doing the same… but for transformer attention.👇 🔗 yoterel.github.io/attention_chai…