GaussianCube: Structuring Gaussian Splatting using Optimal Transport for 3D Generative Modeling

arXiv:2403.19655v1 Announce Type: new
Abstract: 3D Gaussian Splatting (GS) have achieved considerable improvement over Neural Radiance Fields in terms of 3D fitting fidelity and rendering speed. However, this unstructured representation with scattered Gaussians poses a significant challenge for generative modeling. To address the problem, we introduce GaussianCube, a structured GS representation that is both powerful and efficient for generative modeling. We achieve this by first proposing a modified densification-constrained GS fitting algorithm which can yield high-quality fitting results using a …

abstract arxiv challenge cs.cv fidelity fields generative generative modeling however improvement modeling neural radiance fields rendering representation speed terms transport type unstructured