Gaussian Difference: Find Any Change Instance in 3D Scenes
This addresses the problem of detecting object-level changes in real-world 3D environments for applications like surveillance or monitoring, representing a strong incremental advance over existing methods.
The paper tackles instance-level change detection in 3D scenes under uncontrolled conditions like varying lighting and camera poses, achieving state-of-the-art performance with improved accuracy and robustness to lighting changes compared to methods like C-NERF and CYWS-3D.
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.