VGGT-CD: Training-Free Robust Registration for 3D Change Detection

TL;DR

VGGT-CD is a training-free, robust 3D change detection pipeline that improves registration accuracy and efficiency using a decoupled, multi-stage approach with theoretical guarantees.

Contribution

It introduces a novel training-free method that separates registration from change detection, addressing scale ambiguity and noise issues in 3D scene analysis.

Findings

Reduces Absolute Trajectory Error by 44% outdoors and 59% indoors.

Over 6 times faster registration process.

Produces high-purity 3D change maps without task-specific training.

Abstract

3D change detection from multi-view images is essential for urban monitoring, disaster assessment, and autonomous driving. However, existing methods predominantly operate in the 2D domain, where viewpoint variations are mistaken for physical changes and depth is unavailable. While visual geometry foundation models like VGGT rapidly produce dense point clouds from unposed images, independent per-epoch reconstruction encounters fundamental obstacles: unpredictable inter-epoch scale ambiguity, registration-change paradox where scene changes corrupt alignment, and pervasive edge-flying noise. To address these challenges, we present VGGT-CD, a training-free pipeline decoupling cross-temporal registration from dynamic-change interference. In the Coarse Stage, sparse keyframe joint inference establishes a unified metric space and yields an initial Sim(3) prior. In the Fine Stage, dense reconstructions are purified by isolating static-background correspondences. A closed-form centroid alignment refines the translation while locking scale and rotation, using a residual self-check to mathematically guarantee non-degradation. Evaluated on an 11-scene benchmark from the World Across Time dataset, VGGT-CD reduces Absolute Trajectory Error by 44% outdoors and 59% indoors. It completes registration over 6 times faster, producing high-purity 3D change maps without task-specific training.