🔥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

The first project of my PhD, Generative Rendering, will be presented at #CVPR2024! Generative Rendering is a framework that directly renders low-fidelity animated meshes to animations, enabling a creator to seamlessly create very basic geometry and motion modeling in Blender

We present TeSMo (research.nvidia.com/labs/toronto-a… ), a text-controlled scene-aware motion generation method based on denoising diffusion models. It’s an exciting collaboration with Justus Thies, Michael Black, Jason Peng, Davis Rempe. (1/7)

🚀 The material for the tutorial on "Diffusion Models for Visual Computing" at #Eurographics2024 can now be found at geometry.cs.ucl.ac.uk/courses/diffus… Congrats team!

After years of exploration of fully differentiable mesh—including both vertex features and mesh connectivity, we've finally developed the solution and excited to introduce DMesh, a versatile formulation suitable for closed, open, and mixed surfaces. sonsang.github.io/dmesh-project/

Thanks Dreaming Tulpa 🥓👑 for sharing! Given a video, SynCHMR reconstructs human motion, camera path & scene all in one global coordinate🔥 Will be presented in #CVPR2024. Great collaboration with Yizhou Zhao, Tuanfeng Wang, Jimei Yang, Bhiksha Raj and Min Xu. paulchhuang.github.io/synchmr

Come join us at our course "Diffusion Models for Visual Content Generation" at 2 PM today at #SIGGRAPH2024 with an excellent set of contributors including Niloy Mitra, Minhyuk Sung, Paul Guerrero, Daniel Cohen-Or, Paul Huang and Or Patashnik !

🚀 Our SIGGRAPH 2024 course on "Diffusion Models for Visual Computing" introduces diffusion models from the basics to applications. Check out the website now. geometry.cs.ucl.ac.uk/courses/diffus… w/ Niloy Mitra, Duygu Ceylan, Or Patashnik, Daniel Cohen-Or, Paul Guerrero, and Paul Huang

We released Digital Salon's code and the installation on both linux and windows!

We will present Digital Salon at Siggraph Asia Real-Time Live on next Friday in Tokyo! Project page: digital-salon.github.io Open source code: github.com/digital-salon/…

🚀 I'll be in #NeurIPS2024 presenting ActAnywhere with Boxiao Pan. It out-paints the video background given foreground masks. Poster Session 1 East (11am) on 12.11 Wed. Drop by and say hi! Website: actanywhere.github.io Preprint: arxiv.org/abs/2401.10822

Thanks to Dr. Xu for sharing! MfH estimates metric depths by leveraging generatively painted humans as landmarks. Great collaboration with Hengwei, Kaihua Chen, Pengliang Ji, liao qu, Claire Lin, Weichen Yu, Devin, Hhhhhhao, Jun Shen, Bhiksha Raj, and Min Xu!

We present Track4Gen, which augments video generators with point tracking supervision, effectively reducing unrealistic drift/morphs in object appearance & shape. Led by our talented intern Hyeonho Jeong together with Duygu Ceylan and Niloy Mitra. hyeonho99.github.io/track4gen/

VideoHandles — moving a object around in a video realistically. Accepted to #CVPR2025 🚀 [Project Page]: videohandles.github.io [arXiv]: arxiv.org/abs/2503.01107 Great collaboration with Juil Koo Duygu Ceylan Paul Guerrero and Minhyuk Sung

🎉 Training video diffusion and video point tracking jointly --> more coherent object shapes in the generated videos, e.g. the horn of the yak below. -project: hyeonho99.github.io/track4gen/ Hyeonho Jeong Duygu Ceylan, Niloy Mitra #CVPR2025