Is there anything left? Measuring semantic residuals of objects removed from 3D Gaussian Splatting
This addresses privacy concerns in 3D scene sharing by evaluating removal effectiveness, though it is incremental as it builds on existing scene representations.
The paper tackles the problem of measuring how much of a removed object remains in a 3D scene after editing, particularly for privacy-preserving mapping, and finds that proposed metrics are meaningful and consistent with user studies.
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.