GP-4DGS：基于变分高斯过程的单目视频概率 4D 高斯泼溅
GP-4DGS: Probabilistic 4D Gaussian Splatting from Monocular Video via Variational Gaussian Processes
把变分高斯过程与诱导点引入 4D 高斯泼溅的形变场建模，为单目动态重建提供可训练的不确定性输出与时序外推能力；做动态场景重建或需要判断运动歧义区域的工作可直接复用其时空核与变分推断方案。
原文依据 we design spatio-temporal kernels that capture the correlation structure of deformation fields and adopt variational Gaussian Processes with inducing points for tractable inference
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 GP-4DGS，一个将高斯过程（GP）融入 4D 高斯泼溅（4DGS）的新框架，用于对动态场景进行有原则的概率建模。现有 4DGS 方法侧重于确定性重建，在捕捉运动歧义方面存在固有局限，且缺乏评估预测可靠性的机制。借助高斯过程基于核的概率特性，本方法引入三项关键能力：(i) 运动预测的不确定性量化；(ii) 对未观测或稀疏采样区域的运动估计；(iii) 超出已观测训练帧的时序外推。为将高斯过程扩展到 4DGS 中数量庞大的高斯基元，我们设计了能够捕捉形变场相关结构的时空核，并采用带诱导点的变分高斯过程以实现可处理的推断。实验表明，GP-4DGS 在提升重建质量的同时提供了可靠的不确定性估计，能够有效识别高运动歧义区域。通过应对这些挑战，本工作朝着连接概率建模与神经图形学迈出了有意义的一步。
英文原文摘要 1189 字符
We present GP-4DGS, a novel framework that integrates Gaussian Processes (GPs) into 4D Gaussian Splatting (4DGS) for principled probabilistic modeling of dynamic scenes. While existing 4DGS methods focus on deterministic reconstruction, they are inherently limited in capturing motion ambiguity and lack mechanisms to assess prediction reliability. By leveraging the kernel-based probabilistic nature of GPs, our approach introduces three key capabilities: (i) uncertainty quantification for motion predictions, (ii) motion estimation for unobserved or sparsely sampled regions, and (iii) temporal extrapolation beyond observed training frames. To scale GPs to the large number of Gaussian primitives in 4DGS, we design spatio-temporal kernels that capture the correlation structure of deformation fields and adopt variational Gaussian Processes with inducing points for tractable inference. Our experiments show that GP-4DGS enhances reconstruction quality while providing reliable uncertainty estimates that effectively identify regions of high motion ambiguity. By addressing these challenges, our work takes a meaningful step toward bridging probabilistic modeling and neural graphics.