Automatic 3DGS edits train an online Bayesian scene-change detector

arXivarXivPapers

Automatic 3DGS edits train an online Bayesian scene-change detector
arXiv / Changrui Zhu and Simon Julier

Changrui Zhu and Simon Julier present a method for online scene change detection that updates change beliefs as new images arrive using generalised Bayesian evidence fusion. The prior probability of change and the evidence models are unknown beforehand, so they are learned offline from automatic edits to a reference 3D Gaussian Splatting model, which generate labelled training views without manual annotations.

Online prediction combines current evidence with historical support, and closed-form local Bayes factors update an accumulated 3D Gaussian field, with object-guided refinement producing the final masks. The method reaches 67.64% mIoU on PASLCD and 75.82% on CCS3D, and on PASLCD the complete pipeline runs at 17.2 frames per second over complete query sequences, the fastest among the evaluated online methods.