AI can transfer material of an object in an image to match a material from an example image! The method is called ZeST and it can also perform multiple material edits in a single image and perform implicit lighting-aware edits on the rendering of a textured mesh. Links ⬇️

🔄 ZeST: Zero-Shot Material Transfer from a Single Image 💫 Jupyter Notebook + Replicate 🥳 Thanks to Ta-Ying Cheng ❤ Prafull Sharma ❤ Andrew Markham ❤ Niki Trigoni ❤ Varun Jampani ❤ 🌐page: ttchengab.github.io/zest/ 📄paper: arxiv.org/abs/2404.06425 🧬code:

MeshLRM Large Reconstruction Model for High-Quality Mesh We propose MeshLRM, a novel LRM-based approach that can reconstruct a high-quality mesh from merely four input images in less than one second. Different from previous large reconstruction models (LRMs) that focus on

📜 With my collaborators, Yi Zhou, Matheus Gadelha, Yang , Zexiang Xu (Adobe), and advisor, Ming C. Lin (UMD), we introduce our new paper, DMesh! It formulates existence probability of faces in a mesh to make it differentiable. (1/9) 🔗 Project page: sonsang.github.io/dmesh-project/

New Gradio demo for ZeST thanks to Sylvain Filoni !

ZeST 🍋 Material Transfer demo is featured this week ! 🤟 Explore Hugging Face Spaces of the Week —> hf.co/spaces

Looking forward to sharing the work soon at #CHI2024!

#CVPR2024 is fast approaching so I wrote a short summary of the works we will be presenting there. Their goal is to improve our understanding of the inner workings of text2img models while allowing users to better control this fascinating tool. mgadelha.me/directing_imag…

This week I will be attending #CVPR2024 in Seattle! We will be presenting three papers (all in Session 2): * Continuous 3D Words, led by Ta-Ying Cheng, P190 * Generative Rendering, led by Shengqu Cai, P273 * Diffusion Handles, led by Karran Pandey, P281

I will be presenting today at #CVPR2024 ! Drop by our poster session to learn more about Continuous 3D Words for text-to-image generation: Time & Place: 19 Jun 5pm / Arch 4A-E P190 Project page: ttchengab.github.io/continuous_3d_…

Thrilled to share that ZeST has been accepted to #ECCV2024 !! A huge thanks to my collaborators/mentors Prafull Sharma , Varun Jampani, and my supervisors Niki Trigoni and Andrew Markham for the amazing support!

Amazing work combining a variety of 3D models with LLMs for better spatial reasoning! Chenyang "Danny" Ma

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

3D-guided image generation in Project Neo! Had a lot of fun working on this tech! Great to see it in the hands of the users -- make sure to try it out at projectneo.adobe.com