Article

Any 3D Scene is Worth 1K Tokens: A Paper on Scene Generation in 3D Latent Space

The paper proposes performing 3D scene generation directly in a high-dimensional implicit 3D latent space derived from 2D foundation models (such as DINOv2, SigLIP2, and DA3), using a diffusion Transformer to model within that 3D latent space and achieve 3D-grounded scene generation.

Part of the event: Paper proposes directly generating 3D scenes in 3D latent space

This page provides a summary and source link only.