Newest papers

Learning from Automatic 3D Gaussian Splatting Edits for Online Bayesian Scene Change Detection

Changrui Zhu, Simon Julier · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28490 · cited by 0 works (OpenAlex) · open-access PDF

German

Online-Szenenwechselerkennung erfordert die Integration eingehender Beobachtungen, um festzustellen, welche Regionen sich in Bezug auf eine Referenzszene geändert haben. Wir aktualisieren Veränderungsüberzeugungen, wenn neue Bilder mithilfe der generalisierten Bayesian-Beweisfusion ankommen. Allerdings sind die vorherige Wahrscheinlichkeit von Veränderungen und Beweismodellen vorher unbekannt, und die numerische Bayesian-Inferenz kann kostspielig sein. Wir bewältigen diese Herausforderungen, indem wir offline von automatischen Bearbeitungen zu einem Referenz 3D Gaussian Splatting (3DGS) Modell lernen. Diese Bearbeitungen erzeugen markierte Trainingsansichten ohne manuelle Anmerkungen. Zusammen mit unveränderten Referenzbeobachtungen bieten sie die Überwachung für Lernszenenspezif

Machine translation (Meta M2M100); the English original follows.

Abstract

Online scene change detection requires integrating incoming observations to determine which regions have changed relative to a reference scene. We update change beliefs as new images arrive using generalised Bayesian evidence fusion. However, the prior probability of change and evidence models are unknown beforehand, and numerical Bayesian inference can be costly. We address these challenges by learning offline from automatic edits to a reference 3D Gaussian Splatting (3DGS) model. These edits generate labelled training views without manual annotations. Together with unchanged reference observations, they provide supervision for learning scene-specific evidence models and estimating the effective pixel prior and response statistics. Online prediction combines current evidence with historical support, while closed-form local Bayes factors, parameterized by the learned response statistics, update an accumulated 3D Gaussian field. Object-guided refinement produces the final change masks. Our method achieves state-of-the-art accuracy on PASLCD and CCS3D, with $67.64\%$ and $75.82\%$ mIoU, respectively. On PASLCD, the complete pipeline runs at $17.2$\,FPS over complete query sequences, the fastest among the evaluated online methods.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Change detection, Artificial intelligence, Bayesian probability, Inference, Gaussian process

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange