paper-with-me

홈 › Papers

Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation

2026-07-23 · Hyunmin Cho, Jaejun Yoo, Kyong Hwan Jin 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.

📄 PDF Abstract BibTeX arXiv:2607.21485

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DiGS : Divergence guided shape implicit neural representation for unoriented point clouds

2021-06-21 · Yizhak Ben-Shabat, Chamin Hewa Koneputugodage, Stephen Gould

Shape implicit neural representations (INRs) have recently shown to be effective in shape analysis and reconstruction tasks. Existing INRs require point coordinates to learn the implicit level sets of the shape. When a n…

Representation LearningSurface Reconstruction

SASNet: Spatially-Adaptive Sinusoidal Neural Networks

2025-03-12 · Haoan Feng, Diana Aldana, Tiago Novello, Leila De Floriani

Sinusoidal neural networks (SNNs) have emerged as powerful implicit neural representations (INRs) for low-dimensional signals in computer vision and graphics. They enable high-frequency signal reconstruction and smooth m…

Super-Resolution

DiGS: Divergence Guided Shape Implicit Neural Representation for Unoriented Point Clouds

2022-01-01 · CVPR 2022 1 · Yizhak Ben-Shabat, Chamin Hewa Koneputugodage, Stephen Gould

Shape implicit neural representations (INR) have recently shown to be effective in shape analysis and reconstruction tasks. Existing INRs require point coordinates to learn the implicit level sets of the shape. When …

Representation LearningSurface Reconstruction

Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks

2025-01-01 · CVPR 2025 1 · Tiago Novello, Diana Aldana, Andre Araujo, Luiz Velho

Sinusoidal neural networks have been shown effective as implicit neural representations (INRs) of low-dimensional signals, due to their smoothness and high representation capacity. However, initializing and training …

Implicit Neural Representations and the Algebra of Complex Wavelets

2023-10-01 · T. Mitchell Roddenberry, Vishwanath Saragadam, Maarten V. de Hoop, Richard G. Baraniuk

Implicit neural representations (INRs) have arisen as useful methods for representing signals on Euclidean domains. By parameterizing an image as a multilayer perceptron (MLP) on Euclidean space, INRs effectively represe…