LT3SD: Latent Trees for 3D Scene Diffusion

quan-meng.github.io/projects/lt3sd Figure 1 . We introduce LT3SD, a novel latent 3D scene diffusion approach enabling high-fidelity generation of infinite 3D environments. We train LT3SD on a latent tree-based 3D scene representation, encoding both lower-frequency geometry and higher-frequency detail, and synthesize infinite scenes in a patch-by-patch and coarse-to-fine fashion.