3DGS-CD: 3D Gaussian Splatting-Based Change Detection for Physical Object Rearrangement
Ziqi Lu, Jianbo Ye, John Leonard · IEEE Robotics and Automation Letters · 2025
We present 3DGS-CD, the first 3D Gaussian Splatting (3DGS)-based method for detecting physical object rearrangements in 3D scenes. Our approach estimates 3D object-level changes by comparing two sets of unaligned images taken at different times. Leveraging 3DGS's novel view rendering and EfficientSAM's zero-shot segmentation capabilities, we detect 2D object-level changes, which are then associated and fused across views to estimate 3D change masks and object transformations. Our method canaccuratelyidentify changes incluttered environmentsusingsparse(as few as one) post-change images within as little as18 s. It does not rely on depth input, user instructions, pre-defined object classes, or object models – An object is recognized simply if it has been re-arranged. Our approach is evaluated on both public and self-collected real-world datasets, achieving up to14% higher accuracyandthree orders of magnitude fasterperformance compared to the state-of-the-art radiance-field-based change detection method. This significant performance boost enables a broad range of downstream applications, where we highlight threekey use cases:object reconstruction, robot workspace reset, and 3DGS model update.