GP-4DGS：通过变分高斯过程从单目视频中进行概率性4D高斯点溅射
GP-4DGS: Probabilistic 4D Gaussian Splatting from Monocular Video via Variational Gaussian Processes
AI总结：
本文提出GP-4DGS框架，结合高斯过程与4D高斯点溅射，实现动态场景的概率建模。通过引入不确定性量化、运动估计和时间外推，提升重建质量与预测可靠性。
摘要：
我们提出GP-4DGS，一种将高斯过程（GPs）整合到4D高斯点溅射（4DGS）中的新框架，以实现动态场景的原理性概率建模。尽管现有4DGS方法专注于确定性重建，但它们在捕捉运动模糊性和缺乏预测可靠性评估机制方面存在固有局限。通过利用基于核的概率性质，我们的方法引入了三个关键能力：（i）运动预测的不确定性量化，（ii）未观测或稀疏采样区域的运动估计，以及（iii）超出观测训练帧的时间外推。为了将GPs扩展到4DGS中的大量高斯原始体，我们设计了时空核，捕捉变形场的相关结构，并采用带有诱导点的变分高斯过程以实现可计算的推断。我们的实验表明，GP-4DGS在提升重建质量的同时，提供了可靠的不确定性估计，有效识别高运动模糊区域。通过解决这些挑战，我们的工作在概率建模与神经图形学之间迈出了重要一步。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
