paper-with-me

홈 › Papers

H-SIREN: Improving implicit neural representations with hyperbolic periodic functions

2024-10-07 · Rui Gao, Rajeev K. Jaiman

Implicit neural representations (INR) have been recently adopted in various applications ranging from computer vision tasks to physics simulations by solving partial differential equations. Among existing INR-based works, multi-layer perceptrons with sinusoidal activation functions find widespread applications and are also frequently treated as a baseline for the development of better activation functions for INR applications. Recent investigations claim that the use of sinusoidal activation functions could be sub-optimal due to their limited supported frequency set as well as their tendency to generate over-smoothed solutions. We provide a simple solution to mitigate such an issue by changing the activation function at the first layer from $\sin(x)$ to $\sin(\sinh(2x))$. We demonstrate H-SIREN in various computer vision and fluid flow problems, where it surpasses the performance of several state-of-the-art INRs.

📄 PDF Abstract BibTeX arXiv:2410.04716

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Implicit Neural Representations with Periodic Activation Functions

2020-06-17 · NeurIPS 2020 12 · Vincent Sitzmann, Julien N. P. Martel, Alexander W. Bergman, David B. Lindell 외

Implicitly defined, continuous, differentiable signal representations parameterized by neural networks have emerged as a powerful paradigm, offering many possible benefits over conventional representations. However, curr…

Image Inpainting

HOSC: A Periodic Activation with Saturation Control for High-Fidelity Implicit Neural Representations

2026-01-10 · Michal Jan Wlodarczyk, Danzel Serrano, Przemyslaw Musialski arxiv

Periodic activations such as sine preserve high-frequency information in implicit neural representations (INRs) through their oscillatory structure, but often suffer from gradient instability and limited control over mul…

Seeing Implicit Neural Representations as Fourier Series

2021-09-01 · Nuri Benbarka, Timon Höfer, Hamd ul-moqeet Riaz, Andreas Zell

Implicit Neural Representations (INR) use multilayer perceptrons to represent high-frequency functions in low-dimensional problem domains. Recently these representations achieved state-of-the-art results on tasks related…

Novel View Synthesis

Guidance and Control Networks with Periodic Activation Functions

2024-05-28 · Sebastien Origer, Dario Izzo

Inspired by the versatility of sinusoidal representation networks (SIRENs), we present a modified Guidance & Control Networks (G&CNETs) variant using periodic activation functions in the hidden layers. We demonstrate tha…

FM-SIREN & FM-FINER: Implicit Neural Representation Using Nyquist-based Orthogonality

2025-09-27 · Mohammed Alsakabi, Wael Mobeirek, John M. Dolan, Ozan K. Tonguz arxiv

Existing periodic activation-based implicit neural representation (INR) networks, such as SIREN and FINER, suffer from hidden feature redundancy, where neurons within a layer capture overlapping frequency components due …