🔥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

Christian Theobalt talking about Neural Models of the Real World at #gcpr #vmv 2024 in Munich

Want to drive your photoreal full-body avatar solely from an egocentric camera? Check out our #SIGGRAPHAsia 2024 work EgoAvatar! Project page: vcai.mpi-inf.mpg.de/projects/EgoAv… Team: JC "Jack" Chen, @jianwangmpi, Marc Habermann @ CVPR, Christian (MPII), and Yinda, Rohit, Thabo (Google)

Can cloth simulation benefit from a neural implicit spatiotemporal deformation field supervised by the Kirchhoff–Love thin plate theory? Answers: Navami Kairanda et al. NeuralClothSim. @NeurIPS2024. Paper: arxiv.org/pdf/2308.12970… Project page & Source code: 4dqv.mpi-inf.mpg.de/NeuralClothSim/ 👇

NeuralClothSim (continued): *uses a non-linear anisotropic material model *allows material interpolation and simulation editing NDFs: *allocate the capacity to the deformation details *allow surface state queries at arbitrary spatial resolutions without retraining

Check out our work "TriHuman: A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesis”, which will be soon presented at #SIGGRAPHAsia2024. Chat with us about creating animatable and photorealistic digital humans!

We will present our #SIGGRAPHAsia work EgoAvatar: Egocentric View Driven and Photorealistic Full-body Avatar at Dec. 05, 4:30 pm-5:40pm Hall B5 (1), B Block, Level 5. See you there! Project page: vcai.mpi-inf.mpg.de/projects/EgoAv…

#SIGGRAPHAsia We present GaussianHeads—A real-time 3D head avatar model using a coarse-to-fine approach for rendering highly deformable head motions. 📅 Session: My Name is Carl: Gaussian Humans 🕥 12/6/2024, 10:45-11:55 📍 Hall B5 (2), B Block, Level 5

Interested in neural cloth simulation? Don't miss our recent work NeuralClothSim at #Neurips 2024. You can find Navami Kairanda at East Exhibit Hall A-C #3911 on Friday 13 Dec 11 a.m. PST — 2 p.m. PST. Project page: 4dqv.mpi-inf.mpg.de/NeuralClothSim/

🚀 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

Can we generate meaningful speech-driven motion by extracting semantics from data? ✅Yes, we can! Check out our latest #CVPR2025 work on generating semantically rich gestures using Diffusion-based RAG 🚀 🎥: vcai.mpi-inf.mpg.de/projects/RAG-G… VCAI - MPI for Informatics #AI #MotionGeneration #EmbodiedAI

Our framework includes: ✅ Diffusion-based approach that injects motion exemplars to generate natural & semantically meaningful gestures. ✅ Explicit Retrieval framework that can use linguistic structures or LLM-based gesture type predictions (or the algorithm of your choice).

Code and models coming soon! Paper: arxiv.org/abs/2412.06786 Videos with explanation: vcai.mpi-inf.mpg.de/projects/RAG-G… Many thanks to the collaborators: Rishabh Dabral Merel Scholman Vera Demberg Christian Theobalt 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. 🧵...

Want to have explicit control over skeletal pose, facial expressions, and hand gestures for your photorealistic virtual avatar that can be learned from multi-view video? Check out our #Siggraph2025 work, EVA, which presents an expressive, full-body, and photorealistic avatar.