BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation. (arXiv:2401.17053v1 [cs.CV])

We present BlockFusion, a diffusion-based model that generates 3D scenes as
unit blocks and seamlessly incorporates new blocks to extend the scene.
BlockFusion is trained using datasets of 3D blocks that are randomly cropped
from complete 3D scene meshes. Through per-block fitting, all training blocks
are converted into the hybrid neural fields: with a tri-plane containing the
geometry features, followed by a Multi-layer Perceptron (MLP) for decoding the
signed distance values. A variational auto-encoder is employed to compress the
tri-planes …

3d scene generation 3d scenes arxiv block cs.cv datasets diffusion meshes per plane through training