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.
@article{arxiv.2603.22786,
title = {Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis},
author = {Chamuditha Jayanga Galappaththige and Thomas Gottwald and Peter Stehr and Edgar Heinert and Niko Suenderhauf and Dimity Miller and Matthias Rottmann},
journal= {arXiv preprint arXiv:2603.22786},
year = {2026}
}