| title | The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation |
|---|---|
| authors | Jeonghwan Cho, Minsu Kim, Junyoung Hong, Seon Joo Kim |
| date | 2026-11-16 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2611.21383 |
| affiliation | Yonsei University |
| upvotes | 31 (Hugging Face Daily Papers, 2026-11-21) |
| links | abs pdf hf code |
| cite | |
| abstract | 3D Gaussian Splatting enables object-level operations on Gaussian primitives, yet existing segmentation methods are largely trained and evaluated through rendered views. This mismatch can produce accurate rendered masks from incomplete 3D selections since alpha-blended feature supervision concentrates learning on dominant contributors while leaving occluded or low-contribution Gaussians weakly supervised. We propose VODA, a plug-and-play supervision objective that exploits local depth structure to group per-pixel contributors and directly supervises all Gaussians in selected depth clusters, bypassing contribution-weighted gradient delivery. To evaluate volumetric completeness, we introduce Removal-3D, a synthetic object-removal benchmark, and the Removal Depth Error (RDE), a metric comparing predicted and ground-truth depth changes. Across four rendering-based baselines, VODA consistently improves volumetric segmentation on Removal-3D while maintaining or improving performance on LERF and ScanNet. Further analysis shows that VODA recovers lower-contribution Gaussians, while simple gradient reweighting and spatial propagation fail to reproduce comparable gains. |
bibtex
@misc{cho2026mask,
title={The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation},
author={Jeonghwan Cho and Minsu Kim and Junyoung Hong and Seon Joo Kim},
year={2026},
eprint={2611.21383},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2611.21383}
}