FNIN combines a Fourier neural operator with attention-based discontinuity weighting and a single weighted least-squares refinement to reconstruct surfaces from normal maps more accurately and faster than previous SfG methods.
Title resolution pending
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
-
FNIN: A Fourier Neural Operator-based Numerical Integration Network for Surface-form-gradients
FNIN combines a Fourier neural operator with attention-based discontinuity weighting and a single weighted least-squares refinement to reconstruct surfaces from normal maps more accurately and faster than previous SfG methods.