Loading...
Loading...
Browse all stories on DeepNewz
VisitIntegration of CAT3D into major 3D modeling software by mid-2025?
Yes • 50%
No • 50%
Software release notes and company announcements
Google Introduces CAT3D for Rapid 3D Scene Generation with Multi-View Diffusion Models
May 17, 2024, 02:01 AM
Google has introduced CAT3D, a new method that generates high-fidelity 3D scenes from any number of real or generated images in under one minute. This innovative technology uses multi-view diffusion models to create novel views, which are then inputted into NeRF/3DGS systems. CAT3D supports various input types, including text, single images, and multiple images, and can render scenes at 60 frames per second in a browser. The project aims to simplify 3D model creation, reducing the need for hundreds of images typically required for high-quality 3D capture. CAT3D also boasts SOTA few-view results.
View original story
Implementation of real-time rendering • 33%
Integration with major VR platforms • 33%
Release of an open-source version • 34%
Virtual Reality • 25%
Augmented Reality • 25%
Natural Language Processing • 25%
Image Generation • 25%
Wins 3 or more awards • 33%
Wins no awards • 33%
Wins 1-2 awards • 33%
16+ patents • 25%
0-5 patents • 25%
6-10 patents • 25%
11-15 patents • 25%