<p>X-ray imaging facilitates non-destructive testing of agricultural products; however, noise in the acquired images and the limitations of existing denoising methods hinder the full restoration of details in the presence of complex noise. To address the current challenges of high noise levels in walnut X-ray images and the difficulty in preserving critical image details after denoising, this study proposes an improved Restormer denoising model for clearer processing of walnut X-ray images. First, batch normalization layers were introduced into the Multi-Dconv Head Transposed Attention mechanism to enhance the model’s understanding of image features. Second, a vertical Total Variation loss function was integrated to suppress high noise levels and extract clearer image features. Experimental results show that the improved Restormer model achieves a Peak Signal-to-Noise Ratio (PSNR) of 37.30, a Structural Similarity Index Measure (SSIM) of 0.9358, and an information entropy of 6.5600, representing improvements of 0.16 dB, 0.0002, and 0.0014, respectively, compared to the original Restormer model. Additionally, the model’s computational complexity is reduced by 12.83 GFLOPs. In terms of PSNR, SSIM, information entropy, and visual quality, the proposed model outperforms DnCNN, U-NET, Uformer, MIRNET, DRUNET, and Restormer, providing clearer images with richer details. Furthermore, on the local dataset, the model also exhibited excellent processing performance, generalization ability, and stability, making it a highly effective solution for walnut X-ray image denoising. The research results can offer a theoretical basis for the efficient image denoising method on walnut X-ray and provide valuable insights for denoising research in other imaging fields.</p>