DiffSplat repurposes image diffusion models to generate multi-view Gaussian splat grids, using a rendering loss for 3D consistency and achieving state-of-the-art text- and image-conditioned 3D generation.
View selection for 3d captioning via diffusion rank- ing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation
DiffSplat repurposes image diffusion models to generate multi-view Gaussian splat grids, using a rendering loss for 3D consistency and achieving state-of-the-art text- and image-conditioned 3D generation.