用可学习单层激活函数提升隐式神经表示的细节表现力
SL$^{2}$A-INR: Single-Layer Learnable Activation for Implicit Neural Representation
- 在传统ReLU MLP中引入可学习的单层激活层
- 在图像、3D重建等任务上显著提升高频细节还原能力
- 适合需要高保真信号建模的研究者和工业应用
隐式神经表示（INR）通过神经网络将坐标映射为属性，在视觉相关领域取得显著进展。然而，INR性能严重依赖多层感知机（MLP）中非线性激活函数的选择。尽管已有多种非线性被研究，现有INR仍难以捕捉高频成分和多样信号类型。本文提出SL²A-INR，一种混合架构：在使用传统ReLU的MLP基础上，加入一个可学习的单层激活函数。该方法在图像表示、3D形状重建和新视角合成等多样化任务中表现更优。大量实验表明，SL²A-INR在准确率、质量与鲁棒性方面均达到新基准。代码已开源于GitHub。
原文摘要 · Abstract (English)
Implicit Neural Representation (INR), leveraging a neural network to transform coordinate input into corresponding attributes, has recently driven significant advances in several vision-related domains. However, the performance of INR is heavily influenced by the choice of the nonlinear activation function used in its multilayer perceptron (MLP) architecture. To date, multiple nonlinearities have been investigated, but current INRs still face limitations in capturing high-frequency components and diverse signal types. We show that these challenges can be alleviated by introducing a novel approach in INR architecture. Specifically, we propose SL$^{2}$A-INR, a hybrid network that combines a single-layer learnable activation function with an MLP that uses traditional ReLU activations. Our method performs superior across diverse tasks, including image representation, 3D shape reconstruction, and novel view synthesis. Through comprehensive experiments, SL$^{2}$A-INR sets new benchmarks in accuracy, quality, and robustness for INR. Our Code is publicly available on~\href{https://github.com/Iceage7/SL2A-INR}{\textcolor{magenta}{GitHub}}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。