An SDF-driven ray and pixel sampler plus new surface losses modestly improve NeuS and Neuralangelo on object-centric datasets, without code release.
IEEE Trans
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Probability-guided Sampler for Neural Implicit Surface Rendering
An SDF-driven ray and pixel sampler plus new surface losses modestly improve NeuS and Neuralangelo on object-centric datasets, without code release.