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

Portuguese

A detecção de mudanças de cena on-line requer a integração de observações de entrada para determinar quais regiões mudaram em relação a uma cena de referência. Atualizamos as crenças de mudança à medida que novas imagens chegam usando a fusão de evidências Bayesianas generalizadas. No entanto, a probabilidade prévia de mudança e os modelos de evidência são desconhecidos antecipadamente, e a inferência Bayesiana numérica pode ser dispendiosa. Nós abordamos esses desafios aprendendo offline de edições automáticas a um modelo de 3D Gaussian Splatting (3DGS) de referência. Essas edições geram visões de treinamento rotuladas sem anotações manuais. Juntamente com observações de referência inalteradas, eles fornecem supervisão para modelos de evidência específicos de cena de aprendizagem e estim

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