A reconstruct-then-generate 3D latent diffusion model produces complete geometry and appearance assets from sparse in-the-wild LiDAR and camera observations of driving scenes.
SCube: Instant large-scale scene reconstruc- tion using voxsplats.arXiv
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GenAssets: Generating in-the-wild 3D Assets in Latent Space
A reconstruct-then-generate 3D latent diffusion model produces complete geometry and appearance assets from sparse in-the-wild LiDAR and camera observations of driving scenes.