BA-GS：面向无SfM三维重建的贝叶斯自适应高斯泼溅
BA-GS: Bayesian Adaptive Gaussian Splatting for SFM-Free 3D Reconstruction
将贝叶斯不确定性建模引入无SfM的高斯泼溅初始化与优化：用变分高斯混合模型建模全局潜变量分布，用自适应卡尔曼滤波融合噪声梯度观测与空间先验来精化每个高斯基元的位置，为稀疏视角下的3DGS提供可复用的概率化优化框架。
原文依据 we propose BA-GS, a Bayesian framework that models both the global distribution and local uncertainty of Gaussian primitives.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论3D高斯泼溅（3DGS）在重建和新视角合成任务中表现出卓越性能。然而，其对运动恢复结构（Structure-from-Motion）预处理的依赖可能在稀疏视角场景下导致性能下降。近期工作尝试利用预训练图像匹配模型生成高斯基元来应对这一局限，但忽略了初始基元分布和迭代位置更新中嵌入的概率不确定性。这种不确定性会累积并降低重建保真度。因此，我们提出BA-GS，一个贝叶斯框架，对高斯基元的全局分布和局部不确定性进行建模。在全局初始化阶段，变分贝叶斯高斯混合模型（VB-GMM）对基元的潜变量分布建模，捕捉区域级的密度和梯度模式。在局部精化阶段，自适应卡尔曼滤波通过递归融合带噪梯度观测与空间先验来精化每个基元的位置，并根据局部不确定性动态调整其协方差。这种分层贝叶斯公式有效连接了概率分布建模与不确定性感知优化，从而在稀疏视角条件下提升了重建质量。在包括Tanks and Temples、MVimgNet和LLFF在内的多个基准数据集上的实验表明，我们的方法持续优于现有方法。
英文原文摘要 1474 字符
3D Gaussian Splatting (3DGS) has demonstrated exceptional performance in reconstruction and novel view synthesis tasks. However, its reliance on Structure-from-Motion preprocessing may lead to degraded performance under sparse-view scenarios. Recent works attempt to address this limitation by leveraging pre-trained image matching models to generate Gaussian primitives but overlook the probabilistic uncertainty embedded in both the initial primitive distribution and iterative position updates. This uncertainty can accumulate and degrade reconstruction fidelity. Hence, we propose BA-GS, a Bayesian framework that models both the global distribution and local uncertainty of Gaussian primitives. At global initialization, a Variational Bayesian Gaussian Mixture Model (VB-GMM) models the latent distribution of primitives, capturing region-wise density and gradient patterns. At local refinement, an Adaptive Kalman Filter refines each primitive's position by recursively fusing noisy gradient observations with spatial priors, dynamically adjusting its covariance according to local uncertainty.This hierarchical Bayesian formulation effectively bridges probabilistic distribution modeling and uncertainty-aware optimization, resulting in improved reconstruction quality under sparse-view conditions. Experiments across multiple benchmark datasets including Tanks and Temples, MVimgNet, and LLFF demonstrate that our method consistently outperforms existing approaches.