FLAIR: Frequency- and Locality-Aware Implicit Neural Representations

TL;DR

FLAIR introduces frequency- and locality-aware mechanisms to improve implicit neural representations, effectively addressing spectral bias and enhancing performance in 2D and 3D vision tasks.

Contribution

The paper proposes BLA and WEGE, novel techniques for joint frequency selection and spatial localization, advancing INR capabilities beyond existing methods.

Findings

Outperforms existing INRs in 2D image representation

Enhances 3D shape reconstruction accuracy

Improves novel view synthesis quality

Abstract

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.