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

Recent advances in online scene change detection relocalise incoming query images against a reference 3D Gaussian Splatting (3DGS) model. Changes are then detected by fusing photometric and foundation-model cues from each query and its pose-matched reference rendering. Per-image normalisation aligns the numerical ranges of different cues for fusion, but makes response strength relative to each image, limiting comparability across views. We address this limitation through scene-specific learning from automatic 3DGS edits. Using only the reference 3DGS, this fully automatic process selects object instances, modifies their appearance or geometry, and renders labelled changed and unchanged examples for training. As query images arrive, a causal generalised Bayesian formulation combines the learned prior with current image evidence, current-view geometric support, and historical support from the previous Gaussian field state. The field is updated through direct evidence accumulation, without iterative gradient optimisation or replay of past frames. Evaluation on PASLCD shows that our pixel pipeline achieves $60.2\%$ mIoU and $73.6\%$ F1, outperforming O-SCD Online by $11.0$ mIoU points. It reduces full-pipeline computation time by an estimated $17.9\%$ and change inference time by a measured $38.9\%$ using the same image cues. Object-guided mask refinement raises performance to $66.5\%$ mIoU and $78.1\%$ F1 while remaining online, exceeding the reported scores of GS-Diff, which requires post-change reconstruction, by $2.1$ mIoU points and $2.3$ F1 points.