AI RESEARCH

From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting

arXiv CS.CV

ArXi:2605.07203v1 Announce Type: new Scene change detection methods built on Gaussian splatting universally follow a render-then-compare paradigm: the pre-change scene is rendered into 2D and compared against post-change images via pixel or feature residuals. This change detection problem with Gaussian Splatting has been treated as a question about pixels; we treat it as a question about primitives. We provide direct evidence that native primitive attributes alone -- position, anisotropic covariance, and color -- carry sufficient signal for scene change detection.