mlsanityData to 14 Oct 2026

Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation

arXiv 2607.21485 ↗First posted 23 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 34 references that are in the map. First posted on arXiv 23 Jul 2026.

Builds on

21 of 34 references.

References · 21

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  8. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  9. 2018On the Spectral Bias of Neural Networkscited by 1,341
  10. 2019Deep Equilibrium Modelscited by 615
  11. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  12. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
9 more
  1. 2019Towards Understanding the Spectral Bias of Deep Learningcited by 174
  2. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  3. 2023FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functionscited by 78
  4. 2021Seeing Implicit Neural Representations as Fourier Seriescited by 50
  5. 2024Tuning the Frequencies: Robust Training for Sinusoidal Neural Networkscited by 19
  6. 2021The Uncanny Similarity of Recurrence and Depthcited by 9
  7. 2023Implicit Neural Representations and the Algebra of Complex Waveletscited by 8
  8. 2025Optimizing Rank for High-Fidelity Implicit Neural Representationscited by 8
  9. 2025Towards Lossless Implicit Neural Representation via Bit Plane Decompositioncited by 5

Built on by

Not cited yet.