3D Scene Change Modeling With Consistent Multi-View Aggregation
This addresses scene monitoring and reconstruction for applications like robotics or mapping, but it is incremental as it builds on existing 3D change detection methods.
The paper tackles the problem of spatial inconsistency and inability to separate pre- and post-change states in 3D scene change detection by proposing SCaR-3D, a framework that uses multi-view aggregation with 3DGS to achieve high accuracy and efficiency, outperforming existing methods.
Change detection plays a vital role in scene monitoring, exploration, and continual reconstruction. Existing 3D change detection methods often exhibit spatial inconsistency in the detected changes and fail to explicitly separate pre- and post-change states. To address these limitations, we propose SCaR-3D, a novel 3D scene change detection framework that identifies object-level changes from a dense-view pre-change image sequence and sparse-view post-change images. Our approach consists of a signed-distance-based 2D differencing module followed by multi-view aggregation with voting and pruning, leveraging the consistent nature of 3DGS to robustly separate pre- and post-change states. We further develop a continual scene reconstruction strategy that selectively updates dynamic regions while preserving the unchanged areas. We also contribute CCS3D, a challenging synthetic dataset that allows flexible combinations of 3D change types to support controlled evaluations. Extensive experiments demonstrate that our method achieves both high accuracy and efficiency, outperforming existing methods.