A framework for robust 3D segmentation in editable Gaussian Splatting that combines SAM-HQ masks with prior-guided multiview-consistent label assignment to 3D Gaussians.
To achieve precise boundary segmen- tation, we developed a preprocessing pipeline with a noise removal module to generate high-quality, view-consistent masks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting
A framework for robust 3D segmentation in editable Gaussian Splatting that combines SAM-HQ masks with prior-guided multiview-consistent label assignment to 3D Gaussians.