3DGS-CD: 3D Gaussian Splatting-Based Change Detection for Physical Object Rearrangement

摘要

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 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">accurately</i> identify changes in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">cluttered environments</i> using <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">sparse</i> (<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">as few as one</i>) post-change images within as little as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">18 s</i>. 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 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">14% higher accuracy</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">three orders of magnitude faster</i> 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 <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">key use cases:</i> object reconstruction, robot workspace reset, and 3DGS model update.