Gaussian Difference: Find Any Change Instance in 3D Scenes

TL;DR

This paper introduces a novel 4D Gaussian-based method for instance-level change detection in 3D scenes, effectively handling uncontrolled environments with lighting variations and without requiring labeled image pairs or consistent camera poses.

Contribution

The proposed approach leverages 4D Gaussians for embedding images, enabling robust change detection and categorization in challenging real-world 3D scenarios, outperforming existing methods.

Findings

Outperforms state-of-the-art methods like C-NERF and CYWS-3D.

Robust to lighting variations and environmental changes.

Provides efficient and accurate change detection results.

Abstract

Instance-level change detection in 3D scenes presents significant challenges, particularly in uncontrolled environments lacking labeled image pairs, consistent camera poses, or uniform lighting conditions. This paper addresses these challenges by introducing a novel approach for detecting changes in real-world scenarios. Our method leverages 4D Gaussians to embed multiple images into Gaussian distributions, enabling the rendering of two coherent image sequences. We segment each image and assign unique identifiers to instances, facilitating efficient change detection through ID comparison. Additionally, we utilize change maps and classification encodings to categorize 4D Gaussians as changed or unchanged, allowing for the rendering of comprehensive change maps from any viewpoint. Extensive experiments across various instance-level change detection datasets demonstrate that our method significantly outperforms state-of-the-art approaches like C-NERF and CYWS-3D, especially in scenarios with substantial lighting variations. Our approach offers improved detection accuracy, robustness to lighting changes, and efficient processing times, advancing the field of 3D change detection.