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

2026-01-27

AI Summary

Existing 4D Gaussian splatting methods struggle to handle data uncertainties such as sparse viewpoints, missing frames, or asynchronous camera captures. To address this limitation, this work proposes GraphiXS—the first unified framework based on probabilistic graphical models that integrates Gaussian and Student’s-t distribution primitives into 4D Gaussian splatting, enabling systematic modeling of diverse data uncertainties. By generalizing conventional deterministic representations to probabilistic ones, GraphiXS seamlessly integrates with existing architectures while preserving their structural advantages. Experimental results demonstrate that GraphiXS significantly outperforms current approaches across various scenarios involving missing or corrupted data, exhibiting superior robustness and generalization. This advancement represents a substantive step toward a probabilistic paradigm in 4D neural rendering.

Technology Category

• Reasoning under Uncertainty: Graphical Models
• Machine Learning: Probabilistic Circuits and Graphical Models
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Security and Privacy: Data transparency and provenance
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Gaussian Splatting
• data uncertainty
• 4D reconstruction
• neural rendering
• probabilistic modeling

Innovation

• Gaussian Splatting
• data uncertainty
• probabilistic modeling
• 4D reconstruction
• GraphiXS