GP-4DGS: Probabilistic 4D Gaussian Splatting from Monocular Video via Variational Gaussian Processes

TL;DR

GP-4DGS introduces a probabilistic framework integrating Gaussian Processes into 4D Gaussian Splatting, enabling uncertainty quantification, motion estimation in sparse regions, and temporal extrapolation in dynamic scene reconstruction.

Contribution

It presents a scalable variational Gaussian Process approach for probabilistic 4D scene modeling, addressing motion ambiguity and prediction reliability.

Findings

Enhanced reconstruction quality with uncertainty estimates

Effective motion prediction in unobserved regions

Ability to extrapolate temporally beyond training data

Abstract

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.