A geometry-aware encoding stores trainable feature vectors on triangle surfaces and outperforms hash grids in speed and often quality for neural ambient occlusion and radiance caching.
: Local Positional Encoding for Multi-Layer Perceptrons
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
-
GATE: Geometry-Aware Trained Encoding
A geometry-aware encoding stores trainable feature vectors on triangle surfaces and outperforms hash grids in speed and often quality for neural ambient occlusion and radiance caching.