用概率模型提升动态场景重建的可靠性与泛化能力
GP-4DGS: Probabilistic 4D Gaussian Splatting from Monocular Video via Variational Gaussian Processes
- 引入变分高斯过程建模动态变化，实现不确定性量化
- 可在稀疏观测区域估计运动，且能外推到未见时间帧
- 适合需要可信预测的自动驾驶、机器人等场景
我们提出GP-4DGS，一种将高斯过程（GPs）融入4D高斯点阵（4DGS）的新框架，实现对动态场景的严谨概率建模。现有4DGS方法多为确定性重建，难以捕捉运动模糊性，也缺乏预测置信度评估机制。通过利用GPs基于核函数的概率特性，本方法具备三项核心能力：(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) 超出训练帧范围的时间外推。为将GPs扩展至4DGS中数量庞大的高斯原语，我们设计了时空核以捕捉形变场的相关结构，并采用带诱导点的变分高斯过程实现可计算的推理。实验表明，GP-4DGS在提升重建质量的同时，能提供可靠的不确定性估计，有效识别高运动模糊区域。该工作推动了概率建模与神经图形学的融合。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。