Graphical X Splatting (GraphiXS): A Graphical Model for 4D Gaussian Splatting under Uncertainty

TL;DR

GraphiXS introduces a probabilistic framework for 4D Gaussian Splatting that systematically models data uncertainty, enhancing robustness in neural rendering applications with incomplete or noisy data.

Contribution

It presents the first comprehensive probabilistic approach to incorporate multiple data uncertainties into 4D Gaussian Splatting, generalizing existing methods.

Findings

Outperforms existing methods with missing or noisy data

Systematically models various types of data uncertainty

Can upgrade existing Gaussian Splatting techniques to handle uncertainty

Abstract

We propose a new framework to systematically incorporate data uncertainty in Gaussian Splatting. Being the new paradigm of neural rendering, Gaussian Splatting has been investigated in many applications, with the main effort in extending its representation, improving its optimization process, and accelerating its speed. However, one orthogonal, much needed, but under-explored area is data uncertainty. In standard 4D Gaussian Splatting, data uncertainty can manifest as view sparsity, missing frames, camera asynchronization, etc. So far, there has been little research to holistically incorporating various types of data uncertainty under a single framework. To this end, we propose Graphical X Splatting, or GraphiXS, a new probabilistic framework that considers multiple types of data uncertainty, aiming for a fundamental augmentation of the current 4D Gaussian Splatting paradigm into a probabilistic setting. GraphiXS is general and can be instantiated with a range of primitives, e.g. Gaussians, Student's-t. Furthermore, GraphiXS can be used to `upgrade' existing methods to accommodate data uncertainty. Through exhaustive evaluation and comparison, we demonstrate that GraphiXS can systematically model various uncertainties in data, outperform existing methods in many settings where data are missing or polluted in space and time, and therefore is a major generalization of the current 4D Gaussian Splatting research.