Remove360: Benchmarking Residuals After Object Removal in 3D Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kocour, Simona, Benbihi, Assia, Sattler, Torsten
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908901088165888
author Kocour, Simona
Benbihi, Assia
Sattler, Torsten
author_facet Kocour, Simona
Benbihi, Assia
Sattler, Torsten
contents An object can disappear from a 3D scene, yet still be detectable. Even after visual removal, modern vision models may infer what was originally present. In this work, we introduce a novel benchmark and evaluation framework to quantify semantic residuals, the unintended cues left behind after object removal in 3D Gaussian Splatting. We conduct experiments across a diverse set of indoor and outdoor scenes, showing that current methods often preserve semantic information despite the absence of visual geometry. Notably, even when removal is followed by inpainting, residual cues frequently remain detectable by foundation models. We also present Remove360, a real-world dataset of pre- and post-removal RGB captures with object-level masks. Unlike prior datasets focused on isolated object instances, Remove360 contains complex, cluttered scenes that enable evaluation of object removal in full-scene settings. By leveraging the ground-truth post-removal images, we directly assess whether semantic presence is eliminated and whether downstream models can still infer what was removed. Our results reveal a consistent gap between geometric removal and semantic erasure, exposing critical limitations in existing 3D editing pipelines and highlighting the need for privacy-aware removal methods that eliminate recoverable cues, not only visible geometry. Dataset and evaluation code are publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11431
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Remove360: Benchmarking Residuals After Object Removal in 3D Gaussian Splatting
Kocour, Simona
Benbihi, Assia
Sattler, Torsten
Computer Vision and Pattern Recognition
An object can disappear from a 3D scene, yet still be detectable. Even after visual removal, modern vision models may infer what was originally present. In this work, we introduce a novel benchmark and evaluation framework to quantify semantic residuals, the unintended cues left behind after object removal in 3D Gaussian Splatting. We conduct experiments across a diverse set of indoor and outdoor scenes, showing that current methods often preserve semantic information despite the absence of visual geometry. Notably, even when removal is followed by inpainting, residual cues frequently remain detectable by foundation models. We also present Remove360, a real-world dataset of pre- and post-removal RGB captures with object-level masks. Unlike prior datasets focused on isolated object instances, Remove360 contains complex, cluttered scenes that enable evaluation of object removal in full-scene settings. By leveraging the ground-truth post-removal images, we directly assess whether semantic presence is eliminated and whether downstream models can still infer what was removed. Our results reveal a consistent gap between geometric removal and semantic erasure, exposing critical limitations in existing 3D editing pipelines and highlighting the need for privacy-aware removal methods that eliminate recoverable cues, not only visible geometry. Dataset and evaluation code are publicly available.
title Remove360: Benchmarking Residuals After Object Removal in 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.11431