.png){kind=icon}
.png){kind=icon}
Return
Cross-Frequency Implicit Neural Representation With Self-Evolving Parameters
.png){kind=icon}
PRE
AI
DOI：10.1109/TPAMI.2026.3679791.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Implicit neural representation (INR) has emerged as a powerful paradigm for visual data representation. However, classical INR methods represent data in the original space mixed with different frequency components, and several feature encoding parameters (e.g., the frequency parameter <inline-formula><tex-math notation="LaTeX">$\omega$</tex-math></inline-formula> or the rank <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula>) need manual configurations. In this work, we propose a self-evolving cross-frequency INR using the Haar wavelet transform (termed CF-INR), which decouples data into four frequency components and employs INRs in the wavelet space. CF-INR allows the characterization of different frequency components separately, thus enabling higher accuracy for data representation. To more precisely characterize cross-frequency components, we propose a cross-frequency tensor decomposition paradigm for CF-INR with self-evolving parameters, which automatically updates the rank parameter <inline-formula><tex-math notation="LaTeX">$R$</tex-math></inline-formula> and the frequency parameter <inline-formula><tex-math notation="LaTeX">$\omega$</tex-math></inline-formula> for each frequency component through self-evolving optimization. This self-evolution paradigm eliminates the laborious manual tuning of these parameters, and learns a customized cross-frequency feature encoding configuration for each dataset. We evaluate CF-INR on a variety of visual data representation and inverse imaging problems, including image regression, inpainting, denoising, and cloud removal. Extensive experiments demonstrate that CF-INR outperforms state-of-the-art methods in each case.
Keywords:
Implicit neural representation
Haar wavelet transform
cross-frequency
parameter auto-learning
tensor decomposition
data recovery
Journal
IF:
18.6
Papers:
831
Citations:
9.8W