用可学习周期激活构建高效图像与3D重建模型
Subtractive Modulative Network with Learnable Periodic Activations
- 引入可学习振荡器生成多频基底，结合调制滤波模块合成高阶谐波
- 图像重建PSNR达40+dB，参数量更少且3D新视角合成表现优
- 适合追求高效率的隐式表示应用，如图像生成与三维重建
我们提出一种新型、参数高效的隐式神经表示架构——减法调制网络（SMN），灵感来自经典减法合成。SMN设计为一个原理清晰的信号处理流程，包含可学习周期激活层（振荡器）以生成多频基底，以及一系列调制掩码模块（滤波器）主动生成高阶谐波。本文提供了理论分析与实证验证。SMN在两个图像数据集上实现超过40 dB的PSNR，重建精度与参数效率均优于当前先进方法。在更具挑战性的3D NeRF新视角合成任务中也表现出一致优势。补充材料见https://inrainbws.github.io/smn/
原文摘要 · Abstract (English)
We propose the Subtractive Modulative Network (SMN), a novel, parameter-efficient Implicit Neural Representation (INR) architecture inspired by classical subtractive synthesis. The SMN is designed as a principled signal processing pipeline, featuring a learnable periodic activation layer (Oscillator) that generates a multi-frequency basis, and a series of modulative mask modules (Filters) that actively generate high-order harmonics. We provide both theoretical analysis and empirical validation for our design. Our SMN achieves a PSNR of $40+$ dB on two image datasets, comparing favorably against state-of-the-art methods in terms of both reconstruction accuracy and parameter efficiency. Furthermore, consistent advantage is observed on the challenging 3D NeRF novel view synthesis task. Supplementary materials are available at https://inrainbws.github.io/smn/.
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。