The article outlines a groundbreaking advancement in 3D generative AI through the development of a single-stage 3D diffusion model that offers significantly improved detail and fidelity in 3D meshes. Accompanying this is the TextureGen model, designed for high-quality texture production, ensuring assets are visually appealing and ready for use. Additionally, new methods enhance view consistency and texture resolution, with plans for internal use in AssetGen 2.0 and future rollout to Horizon creators. The growing popularity of online gaming as a platform for youth underscores the importance of addressing challenges such as VR-induced motion sickness.
Our latest innovation represents a significant leap forward in 3D generative AI research, leveraging a single-stage 3D diffusion model to deliver 3D meshes with dramatically improved detail and fidelity.
For texture generation, it also introduces new methods for improved view consistency, texture in-painting, and increased texture resolution.
We're currently using AssetGen 2.0 internally for 3D worlds creation, and we will roll out later this year to Horizon creators.
When you also consider the adoption of online gaming worlds as a key connective platform for millions of youngsters, that's another reason to believe that this approach is the next logical progression.
Collection
[
|
...
]