🔥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

Introducing 𝗦𝘁𝗮𝗻𝗳𝗼𝗿𝗱-𝗢𝗥𝗕 #NeurIPS2023 A real-world object inverse rendering benchmark consisting of 14 everyday objects captured under 7 in-the-wild scenes, with ground-truth 3D scans, environment maps, and dense multi-view images. 🖥️stanfordorb.github.io

Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. openai.com/sora Prompt: “Beautiful, snowy

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

Introducing Proteus 0.1, REAL-TIME video generation that brings life to your AI. Proteus can laugh, rap, sing, blink, smile, talk, and more. From a single image! Come meet Proteus on Twitch in real-time. ↓ Sign up for API waitlist: apparate.ai/early-access.h… 1/11

Looking forward to European Conference on Computer Vision #ECCV2026! I will be speaking on Mon 09/30 (2:40pm) at the Foundation Models for 3D Humans workshop, about building Human Models for Embodied AI and on Weds 08/02 (4:30pm) about Controllable Human-Object Interaction Synthesis.

I will be presenting CHOIS tomorrow 10/2 in the oral session 4C (1:30-3:30pm) and in the poster session 4 (4:30-6:30 pm, poster id 224). If you also want to try our method, Jiaman Li just released the code and models! Code: github.com/lijiaman/chois… Page: lijiaman.github.io/projects/chois/

FürElise Capturing and Physically Synthesizing Hand Motions of Piano Performance

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models Project website is highly recommended and comes with a web viewer for every presented result. Links in the comments. Contributions (cited): • Novel transformer-based generative relighting architecture.

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 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

Without relying on any 3D interaction data, our ZeroHSI generates human-scene interaction and human-object interaction leveraging powerful video generation models! For example, "The person is sliding down the slide" and "The person is watering flowers with a watering can".

Time to democratize humanoid robots! Introducing ToddlerBot, a low-cost ($6K), open-source humanoid for robotics and AI research. Watch two ToddlerBots seamlessly chain their loco-manipulation skills to collaborate in tidying up after a toy session. toddlerbot.github.io

🚀 New Research on Human-Robot Interaction! 🤖 How can humanoid robots communicate beyond words? Our framework, EMOTION, leverages Large Language Models (LLMs) to dynamically generate expressive gestures, enhancing non-verbal communication in robots. 🤯 Our experiments show