About this paper
A plug-and-play objective, VODA, groups per-pixel contributors by local depth to supervise all Gaussians in selected depth clusters, improving volumetric segmentation and enabling evaluation via Removal-3D and Removal Depth Error.
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…
3D Gaussian SplattingGaussian primitivessegmentationrendered viewsalpha-blended feature supervisionoccluded Gaussianslow-contribution GaussiansVODAplug-and-play supervision objectivelocal depth structure
- Upvotes
- 21
- Authors
- 4
- Published
- Nov 16, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation was first seen on Hugging Face · Daily papers on Nov 20, 2026. Since then it has appeared in 29 checks on 3 different days. Its best position was #4 of 30, reached on Nov 20, 07:29 UTC. It is #8 right now, slipping from #7 to #8 over the last 6 checks.