让神经隐式表示同时懂频率和位置，更准更稳地还原图像与3D形状。
FLAIR: Frequency- and Locality-Aware Implicit Neural Representations
- 设计新型激活函数BLA，兼顾频率选择与空间定位，缓解频谱偏差。
- 用小波能量引导编码，实现频率成分的精准控制，提升训练稳定性。
- 适合需要高精度重建的图像与3D视觉任务，尤其在细节还原上优势明显。
神经隐式表示（INRs）通过神经网络将坐标映射到信号，实现连续且紧凑的表征，在多种视觉任务中取得显著进展。然而，现有INRs缺乏频率选择性和空间局部性，过度依赖冗余信号成分，导致频谱偏差——早期学习低频分量，难以捕捉高频细节。为此，我们提出FLAIR（频率与局部性感知的隐式神经表示），包含两项核心创新：一是带局部化激活（BLA），在时频不确定性原理约束下，通过结构化频率控制和空间局部响应，有效缓解频谱偏差并提升训练稳定性；二是小波能量引导编码（WEGE），利用离散小波变换计算能量得分，显式引导频率信息至网络，实现精确频率选择与自适应带宽控制。该方法在2D图像表示、3D形状重建及新视角合成任务中均显著优于现有INRs。
原文摘要 · Abstract (English)
Implicit Neural Representations (INRs) leverage neural networks to map coordinates to corresponding signals, enabling continuous and compact representations. This paradigm has driven significant advances in various vision tasks. However, existing INRs lack frequency selectivity and spatial localization, leading to an over-reliance on redundant signal components. Consequently, they exhibit spectral bias, tending to learn low-frequency components early while struggling to capture fine high-frequency details. To address these issues, we propose FLAIR (Frequency- and Locality-Aware Implicit Neural Representations), which incorporates two key innovations. The first is Band-Localized Activation (BLA), a novel activation designed for joint frequency selection and spatial localization under the constraints of the time-frequency uncertainty principle (TFUP). Through structured frequency control and spatially localized responses, BLA effectively mitigates spectral bias and enhances training stability. The second is Wavelet-Energy-Guided Encoding (WEGE), which leverages the discrete wavelet transform to compute energy scores and explicitly guide frequency information to the network, enabling precise frequency selection and adaptive band control. Our method consistently outperforms existing INRs in 2D image representation, as well as 3D shape reconstruction and novel view synthesis.
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。