Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness for novel view synthesis (NVS). However, the 3DGS model tends to overfit when trained with sparse posed views, limiting its generalization ability to novel views. In this paper, we alleviate the overfitting problem, presenting a Self-Ensembling Gaussian Splatting (SE-GS) approach. Our method encompasses a $\mathbf{\Sigma}$-model and a $\mathbf{\Delta}$-model. The $\mathbf{\Sigma}$-model serves as an ensemble of 3DGS models that generates novel-view images during inference. We achieve the self-ensembling by introducing an uncertainty-aware perturbation strategy at the training state. We complement the $\mathbf{\Sigma}$-model with the $\mathbf{\Delta}$-model, which is dynamically perturbed based on the uncertainties of novel-view renderings across different training steps. The perturbation yields diverse temporal samples in the Gaussian parameter space without additional training costs. The geometry of the $\mathbf{\Sigma}$-model is regularized by penalizing discrepancies between the $\mathbf{\Sigma}$-model and these temporal samples. Therefore, our SE-GS conducts an effective and efficient regularization across a large number of 3DGS models, resulting in a robust ensemble, the $\mathbf{\Sigma}$-model. Our experimental results on the LLFF, Mip-NeRF360, DTU, and MVImgNet datasets show that our approach improves NVS quality with few-shot training views, outperforming existing state-of-the-art methods. The code is released at: https://sailor-z.github.io/projects/SEGS.html.