ScaLe-INR: Scale and Learn Implicit Neural Representations
作者: Buwaneka Epakanda, Athulya Ratnayake, Pandula Thennakoon, Mario De Silva, Avishka Ranasinghe, Roshan Godaliyadda, Parakrama Ekanayake
分类: cs.CV
发布日期: 2026-06-26
备注: Submitted as a conference paper to NeurIPS 2026
💡 一句话要点
提出ScaLe-INR以解决隐式神经表示中的频谱偏差问题
🎯 匹配领域: 支柱三:空间感知与语义 (Perception & Semantics)
关键词: 隐式神经表示 频谱偏差 多分支架构 方向边缘引导损失 信号重建 计算机视觉 音频处理 三维重建
📋 核心要点
- 隐式神经表示在建模连续信号时存在频谱偏差和信息交叉干扰的问题,影响多尺度现象的捕捉。
- 提出的ScaLe-INR通过多分支架构和方向边缘引导损失,显式匹配信号频谱,解决了频谱交叉干扰。
- 实验结果显示,ScaLe-INR在图像重建上提高了5.16 dB,在音频重建上达到了50.02 dB,超越了所有现有模型。
📝 摘要(中文)
隐式神经表示(INRs)通过多层感知器在建模连续信号方面表现出色,但面临频谱偏差和信息交叉干扰的挑战。为了解决这些问题,本文提出了ScaLe-INR,一种新型多分支架构,通过显式匹配信号的频谱与INR的最佳操作区域,克服了现有方法的局限性。我们引入了方向边缘引导损失,确保功能解耦并最小化任务特定信息泄漏,从而加速收敛并实现高保真信号重建。实验结果表明,ScaLe-INR在图像重建和去噪等多种任务中显著超越现有最先进方法。
🔬 方法详解
问题定义:隐式神经表示(INRs)在处理多尺度信号时,面临频谱偏差和信息交叉干扰的问题,导致高频权重更新干扰低频结构的近似,影响重建效果。
核心思路:ScaLe-INR通过多分支架构,利用方向坐标缩放理论,扩展网络在特定空间轴上的表示带宽,从而显式匹配信号频谱,解决频谱交叉干扰。
技术框架:该架构包含多个分支,每个分支专注于不同频率的信号处理。引入方向边缘引导损失,确保高频分支作为局部边缘滤波器,减少信息泄漏。
关键创新:方向边缘引导损失是本研究的核心创新,通过空间条件稀疏先验,确保功能解耦,显著提高了收敛速度和重建精度。
关键设计:网络结构采用多分支设计,损失函数结合了方向边缘引导损失,确保高频和低频信息的有效分离,优化了网络的训练过程。实验中,ScaLe-INR在图像和音频重建任务中表现出色。
🖼️ 关键图片
📊 实验亮点
在实验中,ScaLe-INR在图像重建任务中比最近的基线提高了5.16 dB,在图像去噪中提高了0.65 dB,音频重建达到了50.02 dB,3D重建的IOU值为0.999,均超越了所有现有最先进模型,显示出显著的性能提升。
🎯 应用场景
ScaLe-INR的研究成果在计算机视觉、音频处理和三维重建等领域具有广泛的应用潜力。通过高效的信号重建能力,该方法可以用于图像增强、去噪、音频恢复等实际场景,推动相关技术的发展与应用。
📄 摘要(原文)
Implicit Neural Representations (INRs) parameterized by multilayer perceptrons excel at modeling continuous signals. However, a key challenge persists as INRs fundamentally suffer from spectral bias and information cross-talk. When a single network attempts to capture multi-scale phenomena, high-frequency weight updates destructively interfere with the underlying low-frequency structural approximation. We introduce Scale and Learn INR (ScaLe-INR), a novel multi-branch architecture that resolves these limitations by explicitly matching the signal's frequency spectrum with the optimal operating region of the INR. Drawing upon the Fourier inverse scaling theorem we demonstrate that applying directional coordinate scaling expands a network's representational bandwidth along specific spatial axes. To mathematically enforce functional disentanglement and minimize task-specific information leakage between branches, we propose a Directional Edge Guidance Loss, a spatially-conditioned sparsity prior derived from ground-truth gradients. By constraining the high-frequency branches to act as strict, localized edge-filters, ScaLe-INR eliminates spectral cross-talk, accelerates convergence, and achieves high-fidelity signal reconstruction on complex multi-scale topologies. We evaluate ScaLe-INR across diverse reconstruction and inverse tasks, demonstrating substantial performance gains over existing state-of-the-art (SOTA) methods. The proposed architecture improves upon the nearest baselines by +5.16 dB in image reconstruction and +0.65 dB in image denoising. Furthermore, it achieve an impressive figure of 50.02 dB on audio reconstruction and 0.999 IOU(Intersection Over Union) on 3D reconstruction which beats the all SOTA models.