Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis

TL;DR

This paper introduces a lightweight, plug-and-play uncertainty estimation method for 3D Gaussian Splatting, enhancing its reliability for autonomous and safety-critical applications by providing pixel-wise, view-dependent uncertainty maps without compromising visual quality.

Contribution

It presents a novel, architecture-agnostic Bayesian-regularized approach for uncertainty estimation in Gaussian Splatting that improves downstream perception tasks.

Findings

Improves active view selection accuracy

Enhances scene change detection reliability

Boosts anomaly detection performance

Abstract

Recent advances in 3D Gaussian Splatting have enabled impressive photorealistic novel view synthesis. However, to transition from a pure rendering engine to a reliable spatial map for autonomous agents and safety-critical applications, knowing where the representation is uncertain is as important as the rendering fidelity itself. We bridge this critical gap by introducing a lightweight, plug-and-play framework for pixel-wise, view-dependent predictive uncertainty estimation. Our post-hoc method formulates uncertainty as a Bayesian-regularized linear least-squares optimization over reconstruction residuals. This architecture-agnostic approach extracts a per-primitive uncertainty channel without modifying the underlying scene representation or degrading baseline visual fidelity. Crucially, we demonstrate that providing this actionable reliability signal successfully translates 3D Gaussian splatting into a trustworthy spatial map, further improving state-of-the-art performance across three critical downstream perception tasks: active view selection, pose-agnostic scene change detection, and pose-agnostic anomaly detection.