Kai He

🚀 Introducing UniRelight, a general-purpose relighting framework powered by video diffusion models. 🌟UniRelight jointly models the distribution of scene intrinsics and illumination, enabling high-quality relighting and intrinsic decomposition from a single image or video.

NVIDIA’s AI watched 150,000 videos… and learned to relight scenes incredibly well! No game engine. No 3D software. And it has an amazing cat demo. 🐱💡 Hold on to your papers! Full video: youtube.com/watch?v=yRk6vG…

We will present the paper this afternoon. Come to chat with us!!

Huuuuge congrats! Well deserved 👍👍

🚀 DiffusionRenderer is now open-source! Check out the code and model: github.com/nv-tlabs/diffu… We will present at #CVPR2025 this Sunday, June 15: 🗣️ Oral Session 6A: 1:00–2:30 PM CDT, Karl Dean Grand Ballroom 🖼️ Poster: 4:00–6:00 PM CDT, ExHall D (Poster #29)

GEN3C #CVPR2025 is now open-sourced @HuggingFace, with code released under Apache 2.0 and model weights under the NVIDIA Open Model License! Code: github.com/nv-tlabs/GEN3C HuggingFace: huggingface.co/nvidia/GEN3C-C… Feel free to reach out if you want to chat or connect! #CVPR2025

Thrilled to share the papers that our lab will present at @CVPR. Learn more in this thread 🧵 and meet @Kai__He, @yash2kant, @Dazitu_616, and our previous visitor @toshiya427 in Nashville! 1/n

📢 Introducing DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models Compared to vanilla DPO, we improve paired data construction and preference label granularity, leading to better visual quality and motion strength with only 1/3 of the data. 🧵

#SIGGRAPH2025 🚀Rodin Gen-2 will start the era of testing time scaling law for 3D #GenAI 👀 Sneak peek to the new foundation of #Rodin Gen-2, BANG, who has been accepted by @SIGGRAPH Journal Track! 🎉 🔥 The final paper is still being prepared, see you soon.

The key features of CAST🌟: 1️⃣Open-Vocabulary Scene Reconstruction 2️⃣Occlusion-Aware 3D Object Generation 3️⃣Generative Model for Alignment 4️⃣Physics-Aware Correction for Realism

What if you could control the weather in any video — just like applying a filter? Meet WeatherWeaver, a video model for controllable synthesis and removal of diverse weather effects — such as 🌧️ rain, ☃️ snow, 🌁 fog, and ☁️ clouds — for any input video.

Yes‼️Introducing one of the new features of #Rodin Gen-2: Generate into Parts🔥 🤯For the first time, 3D GenAI truly understands the underlying structure of objects. Coming June 2025🚀 Demo made with @huggingface @gradio #3D #MCP #b3d #Game #UE #Unity #GenerativeAI

Spatial AI is increasingly important, and the newest papers from #NVIDIAResearch, 3DGRT and 3DGUT, represent significant advancements in enabling researchers and developers to explore and innovate with 3D Gaussian Splatting techniques. 💎 3DGRT (Gaussian Ray Tracing) ➡️…

🚀Excited to introduce GEN3C #CVPR2025, a generative video model with an explicit 3D cache for precise camera control. 🎥It applies to multiple use cases, including single-view and sparse-view NVS🖼️ and challenging settings like monocular dynamic NVS and driving simulation🚗.…