To address the issues of inter-symbol interference and inter-carrier interference in the signal reception process of orthogonal frequency division multiplexing (OFDM) systems,this paper proposes a high-performance channel estimation method based on a deep residual learning network (DRLNet).The method first uses the least squares (LS) algorithm at the receiver to preliminarily estimate the channel information at pilot positions,and inputs this information,regarded as noisy low-resolution data,into the channel estimation model.The model learns the mapping from noisy pilot-based information to the complete denoised channel response.As a result,the model outputs the restored full-channel data,enabling accurate acquisition of channel state information.Simulation results demonstrate that the proposed DRLNet model holds an advantage in accuracy over traditional estimation methods in restoring channel state information,and can accurately reconstruct the channel information under various channel environments.