Is there anything left? Measuring semantic residuals of objects removed from 3D Gaussian Splatting
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_ | 1866917964954992640 |
|---|---|
| author | Kocour, Simona Benbihi, Assia Adam, Aikaterini Sattler, Torsten |
| author_facet | Kocour, Simona Benbihi, Assia Adam, Aikaterini Sattler, Torsten |
| contents | Searching in and editing 3D scenes has become extremely intuitive with trainable scene representations that allow linking human concepts to elements in the scene. These operations are often evaluated on the basis of how accurately the searched element is segmented or extracted from the scene. In this paper, we address the inverse problem, that is, how much of the searched element remains in the scene after it is removed. This question is particularly important in the context of privacy-preserving mapping when a user reconstructs a 3D scene and wants to remove private elements before sharing the map. To the best of our knowledge, this is the first work to address this question. To answer this, we propose a quantitative evaluation that measures whether a removal operation leaves object residuals that can be reasoned over. The scene is not private when such residuals are present. Experiments on state-of-the-art scene representations show that the proposed metrics are meaningful and consistent with the user study that we also present. We also propose a method to refine the removal based on spatial and semantic consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17574 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Is there anything left? Measuring semantic residuals of objects removed from 3D Gaussian Splatting Kocour, Simona Benbihi, Assia Adam, Aikaterini Sattler, Torsten Computer Vision and Pattern Recognition Searching in and editing 3D scenes has become extremely intuitive with trainable scene representations that allow linking human concepts to elements in the scene. These operations are often evaluated on the basis of how accurately the searched element is segmented or extracted from the scene. In this paper, we address the inverse problem, that is, how much of the searched element remains in the scene after it is removed. This question is particularly important in the context of privacy-preserving mapping when a user reconstructs a 3D scene and wants to remove private elements before sharing the map. To the best of our knowledge, this is the first work to address this question. To answer this, we propose a quantitative evaluation that measures whether a removal operation leaves object residuals that can be reasoned over. The scene is not private when such residuals are present. Experiments on state-of-the-art scene representations show that the proposed metrics are meaningful and consistent with the user study that we also present. We also propose a method to refine the removal based on spatial and semantic consistency. |
| title | Is there anything left? Measuring semantic residuals of objects removed from 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.17574 |