A learnable confidence framework in 3D Gaussian Splatting balances photometric and geometric losses while penalizing per-primitive variance to produce state-of-the-art unbounded meshes efficiently.
In: ICRA (2022) 3
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
-
Confidence-Based Mesh Extraction from 3D Gaussians
A learnable confidence framework in 3D Gaussian Splatting balances photometric and geometric losses while penalizing per-primitive variance to produce state-of-the-art unbounded meshes efficiently.