3D Scene Change Modeling With Consistent Multi-View Aggregation

TL;DR

This paper introduces SCaR-3D, a novel framework for 3D scene change detection that improves spatial consistency and explicitly separates pre- and post-change states using multi-view aggregation and a new synthetic dataset.

Contribution

The paper proposes SCaR-3D, a new 3D change detection method with a signed-distance-based differencing module, multi-view voting, and a continual reconstruction strategy, along with the CCS3D dataset.

Findings

Achieves high accuracy and efficiency in 3D change detection

Outperforms existing methods in experiments

Effectively separates pre- and post-change states

Abstract

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.