Model-based interpolation and sparse recovery are compared to a hierarchical Fourier neural operator that learns the mapping from FIM shapes to mmWave channel responses and outperforms baselines in accuracy and pilot efficiency.
Unified array man ifold de- composition based on spherical harmonics and 2-d fourier ba sis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Channel Estimation for Flexible Intelligent Metasurfaces: From Model-Based Approaches to Neural Operators
Model-based interpolation and sparse recovery are compared to a hierarchical Fourier neural operator that learns the mapping from FIM shapes to mmWave channel responses and outperforms baselines in accuracy and pilot efficiency.