| title | Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation |
|---|---|
| authors | Hyunmin Cho, Jaejun Yoo, Kyong Hwan Jin |
| date | 2026-07-23 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2607.21485 |
| upvotes | 7 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | We study sinusoidal recurrence as an iterative mechanism for harmonic spectral enrichment in implicit neural representations (INRs). Our analysis reveals that sinusoidal activations induce a harmonic line spectrum, providing a spectral account of how recurrent unrolling enriches the effective spectral support. We realize this principle with a shared sinusoidal block that iteratively refines the latent representation. We empirically validate the resulting spectral behavior against feed-forward INRs, non-sinusoidal recurrent variants, and equilibrium-style sinusoidal models. Complementing this analysis, we evaluate the proposed architecture across image and 3D representation tasks. On RGB image benchmarks, our method achieves higher fidelity than feed-forward baselines with fewer parameters and fewer optimization steps, and it further transfers favorably to super-resolution, NeRF, and SDF tasks. |
cite
@misc{cho2026recurrent,
title={Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation},
author={Hyunmin Cho and Jaejun Yoo and Kyong Hwan Jin},
year={2026},
eprint={2607.21485},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2607.21485}
}