Reducing Pilots in Channel Estimation with Predictive Foundation Models

TL;DR

This paper presents a novel predictive foundation model framework for wireless channel estimation that reduces pilot overhead, enhances robustness, and improves generalization across diverse scenarios using large-scale cross-domain data and advanced neural architectures.

Contribution

It introduces a universal, predictive foundation model for CSI acquisition that generalizes across environments and employs a vision transformer-based pilot processing network.

Findings

Significantly outperforms classical and data-driven methods in accuracy.

Demonstrates robustness under noisy and sparse pilot conditions.

Achieves superior cross-scenario transferability and generalization.

Abstract

Accurate channel state information (CSI) acquisition is essential for modern wireless systems, which becomes increasingly difficult under large antenna arrays, strict pilot overhead constraints, and diverse deployment environments. Existing artificial intelligence-based solutions often lack robustness and fail to generalize across scenarios. To address this limitation, this paper introduces a predictive-foundation-model-based channel estimation framework that enables accurate, low-overhead, and generalizable CSI acquisition. The proposed framework employs a predictive foundation model trained on large-scale cross-domain CSI data to extract universal channel representations and provide predictive priors with strong cross-scenario transferability. A pilot processing network based on a vision transformer architecture is further designed to capture spatial, temporal, and frequency correlations from pilot observations. An efficient fusion mechanism integrates predictive priors with real-time measurements, enabling reliable CSI reconstruction even under sparse or noisy conditions. Extensive evaluations across diverse configurations demonstrate that the proposed estimator significantly outperforms both classical and data-driven baselines in accuracy, robustness, and generalization capability.