Firehose

Filtered to Papers, tagged “implicit neural representations” · clear filters

23 JUL 2026 · Paper

Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation

This paper develops a new architecture for implicit neural representations (INRs) that uses sinusoidal recurrence to improve the quality of the representations, and it demonstrates that this approach can lead to better image and 3D representations with fewer parameters and less computation.

implicit neural representations recurrent neural networks sinusoidal activations spectral analysis neural image synthesis

Browse by tag

Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation