3DGS-CD: 3D Gaussian Splatting-based Change Detection for Physical Object Rearrangement
This work addresses the problem of change detection in cluttered environments for applications like robotics and 3D modeling, representing a novel method for a known bottleneck.
The paper tackles the problem of detecting physical object rearrangements in 3D scenes by introducing 3DGS-CD, a method that uses 3D Gaussian Splatting and EfficientSAM to estimate 3D object-level changes from unaligned images, achieving up to 14% higher accuracy and three orders of magnitude faster performance compared to state-of-the-art methods.
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 can accurately identify changes in cluttered environments using sparse (as few as one) post-change images within as little as 18s. 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 to 14% higher accuracy and three orders of magnitude faster performance 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 three key use cases: object reconstruction, robot workspace reset, and 3DGS model update. Our code and data will be made available at https://github.com/520xyxyzq/3DGS-CD.