Fast accurate online detection of 3d scene changes using learned models
Learning from Automatic 3D Gaussian Splatting Edits for Online Bayesian Scene Change Detection
Computer Vision and Pattern RecognitionGraphics
Summary
Detecting changes in a 3D scene over time can be difficult because it needs to quickly decide which parts are different from before. The authors developed a method that learns how changes in a 3D model look by using automatic edits without needing humans to label data. Their approach updates beliefs about what changed as new images come in, doing this efficiently and accurately. This helps find changed areas in a scene fast and better than other methods.
What this means in practice
- •For autonomous vehicle engineers: Detect real-time changes in the environment around a vehicle using camera inputs to adjust driving decisions safely.
- •For video surveillance operators: Identify altered or newly introduced objects in monitored 3D scenes quickly to improve security response times.
Authors
Changrui Zhu, Simon Julier
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.