Modeling uncertainty for Gaussian Splatting

arXiv:2403.18476v1 Announce Type: new
Abstract: We present Stochastic Gaussian Splatting (SGS): the first framework for uncertainty estimation using Gaussian Splatting (GS). GS recently advanced the novel-view synthesis field by achieving impressive reconstruction quality at a fraction of the computational cost of Neural Radiance Fields (NeRF). However, contrary to the latter, it still lacks the ability to provide information about the confidence associated with their outputs. To address this limitation, in this paper, we introduce a Variational Inference-based approach that seamlessly …

abstract advanced arxiv computational cost cs.cv cs.gr fields framework however modeling nerf neural radiance fields novel quality sgs stochastic synthesis type uncertainty view