🔥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

Check out our SIGGRAPH ASIA 2020 Paper: Dynamic Facial Asset and Rig Generation from a Single Scan! Great collaboration with Zhengfei Kuang, Real Yajie Zhao, Mingming He, Karl Bladin, and Hao Li! Demo: youtube.com/watch?v=VV655f… Paper: arxiv.org/pdf/2010.00560…

#CVPR Can we estimate human motion from egocentric videos? Check out our Ego-Body Pose Estimation via Ego-Head Pose Estimation (Award Candidate)! w Karen and Jiajun Wu. Poster: THU-AM-063. (I will be on Zoom for Q&A!) Project page: (code is released!) lijiaman.github.io/projects/egoeg…

Check out Stanford-ORB --- a real-world 3D object inverse rendering benchmark in Tue afternoon #NeurIPS2023! Dataset & Code available at stanfordorb.github.io.

Accepted to CVPR! 😇 #CVPR2025 #CVPR2024 Congrats to the team at Stanford and HKUST: Zifan Shi Yifan Wang Yinghao Xu Ryan Po Zhengfei Kuang Qifeng Chen Dit-Yan Yeung and Gordon Wetzstein See you in Seattle!

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation

We've been exploring a fun and challenging idea: combining top-notch video generation models with multi-view capabilities. This seems like a natural next step after all the amazing video and multi-image generation models. The question was, could we create a multi-view video

#ECCV24 We introduce Controllable Human-Object Interaction Synthesis (CHOIS) to generate interactions given text in a 3D scene. w alex, Roozbeh Mottaghi Jiajun Wu Xavier Puig Karen. code: github.com/lijiaman/chois… project page: lijiaman.github.io/projects/chois/

Excited to present our work at NeurIPS 2024! 📍 East Exhibit Hall A-C #1803, ⏰ December 11th, 11 AM - 2 PM With multi-view video diffusion models gaining significant traction recently, we're proud to revisit our pioneering work from earlier this year: Collaborative Video

🔥 Introducing MVLift: Generate realistic 3D motion without any 3D training data - just using 2D poses from monocular videos! Applicable to human motion, human-object interaction & animal motion. Joint work w/ Jiajun Wu & Karen 💡 How? We reformulate 3D motion estimation as

🤖 Introducing Human-Object Interaction from Human-Level Instructions! First complete system that generates physically plausible, long-horizon human-object interactions with finger motions in contextual environments, driven by human-level instructions. 🔍 Our approach: - LLMs