Multi-View Pose-Agnostic Change Localization with Zero Labels

TL;DR

This paper introduces a label-free, pose-agnostic change detection method using multi-view 3D scene representations, achieving state-of-the-art accuracy in complex environments with minimal images.

Contribution

The authors develop a novel multi-view, pose-agnostic change detection approach that leverages 3D Gaussian Splatting and requires only a few images, outperforming existing single-view methods.

Findings

Achieves 1.7x higher IoU and 1.5x higher F1 score than baselines.

Enables accurate change mask generation for unseen viewpoints.

Introduces a new real-world dataset for challenging change detection scenarios.

Abstract

Autonomous agents often require accurate methods for detecting and localizing changes in their environment, particularly when observations are captured from unconstrained and inconsistent viewpoints. We propose a novel label-free, pose-agnostic change detection method that integrates information from multiple viewpoints to construct a change-aware 3D Gaussian Splatting (3DGS) representation of the scene. With as few as 5 images of the post-change scene, our approach can learn an additional change channel in a 3DGS and produce change masks that outperform single-view techniques. Our change-aware 3D scene representation additionally enables the generation of accurate change masks for unseen viewpoints. Experimental results demonstrate state-of-the-art performance in complex multi-object scenes, achieving a 1.7x and 1.5x improvement in Mean Intersection Over Union and F1 score respectively over other baselines. We also contribute a new real-world dataset to benchmark change detection in diverse challenging scenes in the presence of lighting variations.