NG-GS uses NeRF guidance and RBF interpolation on 3DGS to produce smoother, higher-quality object segmentation boundaries.
It begins by identify- ing boundary Gaussians through variance analysis of multi- view 2D masks, where Gaussians with high variance values are selected as ambiguous boundary points
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
-
NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation
NG-GS uses NeRF guidance and RBF interpolation on 3DGS to produce smoother, higher-quality object segmentation boundaries.