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

2024/10/07 by Gao, Rui, Jaiman, Rajeev K. · 3 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2410.04716

Abstract

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.

Cited by

• A nonlinear quantum neural network framework for entanglement engineering
• Missing Wedge Inpainting and Joint Alignment in Electron Tomography through Implicit Neural Representations
• Squeeze3D: Your 3D Generation Model is Secretly an Extreme Neural Compressor

Related

• Implicit Neural Representations with Periodic Activation Functions
• A Unified Theory of Sinusoidal Activation Families for Implicit Neural Representations
• HOSC: A Periodic Activation Function for Preserving Sharp Features in Implicit Neural Representations
• COSMO-INR: Complex Sinusoidal Modulation for Implicit Neural Representations
• Improving Accuracy and Efficiency of Implicit Neural Representations: Making SIREN a WINNER