A 32^3 grid of 13-parameter RBF-weighted polynomial functions fits 3D signed distance fields as accurately as neural hash-grid and octree methods with far fewer parameters.
In Computer Vision–ECCV 2020: 16th Eu- ropean Conference, Glasgow, UK, August 23–28
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
efunc: An Efficient Function Representation without Neural Networks
A 32^3 grid of 13-parameter RBF-weighted polynomial functions fits 3D signed distance fields as accurately as neural hash-grid and octree methods with far fewer parameters.