Gaussian Difference: Find Any Change Instance in 3D Scenes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913704966094848 |
|---|---|
| author | Jiang, Binbin Huang, Rui Zhao, Qingyi Zhang, Yuxiang |
| author_facet | Jiang, Binbin Huang, Rui Zhao, Qingyi Zhang, Yuxiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16941 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Gaussian Difference: Find Any Change Instance in 3D Scenes Jiang, Binbin Huang, Rui Zhao, Qingyi Zhang, Yuxiang Computer Vision and Pattern Recognition 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. |
| title | Gaussian Difference: Find Any Change Instance in 3D Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.16941 |