A bias-free MLP filter applied multiplicatively to Fourier features, with a line-search learning-rate controller, reduces noise and improves implicit neural representation fitting across images, shapes, and NeRF.
bias term tested on the NeRF task
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
-
Robustifying Fourier Features Embeddings for Implicit Neural Representations
A bias-free MLP filter applied multiplicatively to Fourier features, with a line-search learning-rate controller, reduces noise and improves implicit neural representation fitting across images, shapes, and NeRF.