🔥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

Super excited to share the new Roblox Graduate Fellowship program, a 2-year fellowship for PhD students in graphics, machine learning, communications, systems, data science, and economics. The application deadline is August 15, 2024!! gem.com/lp/roblox/ec-r…

🚨SIGGRAPH 2024 Paper Alert 🚨 ➡️Paper Title: Transparent Image Layer Diffusion using Latent Transparency 🌟Few pointers from the paper 🎯In this paper authors have presented an approach enabling large-scale pretrained latent diffusion models to generate transparent images.

Looking forward to getting back to Vancouver! Hope to see you at the talk on Thu Sept 5 11:30-12:30 at SFU Burnaby.

We just released the code for FlashTex: text-to-relightable texture generation for 3D geometry flashtex.github.io Kangle Deng will present this work tomorrow at #ECCV2024

SparseCtrl is a technique for controlling text to video that builds on AnimateDiff and ControlNet. Yuwei Guo will present the technique at #ECCV2024 on Wed Oct 2.

I will present ScriptViz, A Visualization Tool to Aid ScriptWriting based on a Large Movie Database at Mon, 14 Oct | 1:55 PM - 2:10 PM Allegheny 3. #UIST2024 ACM UIST with Maneesh Agrawala Jean-Peïc Chou programs.sigchi.org/uist/2024/prog…

Check our webpage for more details virtualfilmstudio.github.io/projects/scrip…

Happy to have shared artistic insights to help bring our new sketch-to-image generation tool to life 🧑‍🎨🎨! Check out our UIST paper (work with Vishnu Sarukkai, Lu Yuan, Maneesh Agrawala, Kayvon Fatahalian) at miatang13.github.io/BlockAndDetail/. 🦾 Try our live demo (linked in our project page)!

Thank you so much to the #UIST2024 community for recognizing our $1 gesture recognizer work from 2007 with the Lasting Impact Award! Very honored and flattered… Andy Wilson, Yang Li HCI & Design at UW UW iSchool Allen School

github.com/lllyasviel/IC-…

Prof. Maneesh Agrawala Maneesh Agrawala will give a keynote speech at the Computational Visual Media Conference 2025 and AMC AI Film Festival 2025 in Hong Kong. Title: Beyond Unpredictable Black Boxes: Designing Generative AI For Iterative Refinement Abstract: Human creation of

Our relighting work is accepted to #ICLR2025. Paper: openreview.net/pdf?id=u1cQYxR… Code: github.com/lllyasviel/IC-… Demo: huggingface.co/spaces/lllyasv… We impose consistent light (IC-Light) transport during training. This consistency allows for stable and scalable illumination learning, and

Excited to come out of stealth at Reve! Today's text-to-image/video models, in contrast to LLMs, lack logic. Images seem plausible initially but fall apart under scrutiny: painting techniques don't match, props don't carry meaning, and compositions lack intention. (1/4)

Get your tickets and join us + Master of Science in Applied Computing (MScAC) for an upcoming #DataSciencesSpeakerSeries talk: "Unpredictable Black Boxes are Terrible Interfaces" w/ Prof. Maneesh Agrawala from Stanford University 🗓️April 14 📷Info & reg: datasciences.utoronto.ca/event/prof-man…

Great experience at the opening remarks at CVM and HKUST AI Film Festival by Maneesh Agrawala