An optimal transport based geometry embedding, computed independently for each shape, improves accuracy and reduces compute for neural operator predictions of surface pressure and drag on car and airfoil benchmarks.
Implicit neural spatial representations for time-dependent pdes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Geometric Operator Learning with Optimal Transport
An optimal transport based geometry embedding, computed independently for each shape, improves accuracy and reduces compute for neural operator predictions of surface pressure and drag on car and airfoil benchmarks.