Cohere and Fujitsu Announce Strategic Partnership To Provide Japanese Enterprise AI Services
Date: Jul 02, 2024
Time: 3:00 PM - 5:00 PM
Location: Online
This session unveils a novel text-based method for 3D content editing, utilizing 2D model semantics for intuitive shape localization and texture mapping. By forgoing extensive 3D datasets and using neural optimization with pre-trained 2D models, we will explore how the technique enhances texture and detail, providing unparalleled control over 3D modifications through simple text instructions.
Dales's Bio: Dale is a PhD student at the University of Chicago’s 3DL (threedle) lab (https://3dl.cs.uchicago.edu/) studying computer graphics, 3D computer vision, and deep learning. Dale is advised by Rana Hanocka.
The associated papers for the session are @ https://arxiv.org/abs/2212.11263 and @ https://arxiv.org/abs/2311.09571
Add event to calendar