Face super-resolution technology can significantly enhance the resolution and quality of face images, which is crucial for applications such as surveillance, forensics, and face recognition. However, existing methods often fail to fully utilize multi-scale information and facial priors, resulting in poor recovery of facial structures in complex images. To address this issue, we propose a face super-resolution method based on iterative collaboration between a facial reconstruction network and a landmark estimation network. This method employs a Multi-Convolutional Attention Block for multi-scale feature extraction, and an Attention Fusion Block is introduced to enhance features using facial priors. Subsequently, features are further refined using a Residual Window Attention Group. Furthermore, the method involves iterative collaboration between the facial reconstruction network and the landmark estimation network. At each step, landmark priors are used to generate higher quality images, which are then utilized for improved landmark estimation, thereby gradually enhancing performance. Through evaluation of the standard 4\(\times \), 8\(\times \), and 16\(\times \) super-resolution tasks on the CelebA and Helen datasets, This method demonstrates strong performance and achieves competitive scores on SSIM, PSNR, and LPIPS metrics. Specifically, in the 8\(\times \) super-resolution experiment, the PSNR/SSIM/LPIPS on CelebA dataset is 27.68dB/ 0.8112/0.0866, outperforming existing state-of-the-art methods in terms of both accuracy and visual quality.

人脸超分辨率技术可以显著提高人脸图像的分辨率和质量，这对于监控、取证和人脸识别等应用至关重要。然而，现有的方法往往无法充分利用多尺度信息和面部先验，导致复杂图像中面部结构的恢复效果不佳。为了解决这个问题，我们提出了一种基于面部重建网络和地标估计网络之间迭代协作的人脸超分辨率方法。该方法采用多卷积注意力块进行多尺度特征提取，并引入注意力融合块以使用面部先验增强特征。随后，使用 Residual Window Attention Group 进一步细化特征。此外，该方法涉及面部重建网络和地标估计网络之间的迭代协作。在每个步骤中，特征点先验用于生成更高质量的图像，然后用于改进特征点估计，从而逐渐提高性能。通过在 CelebA 和 Helen 数据集上评估标准的 4\（\times \）、8\（\times \） 和 16\（\times \） 超分辨率任务，该方法展示了强大的性能，并在 SSIM、PSNR 和 LPIPS 指标上取得了有竞争力的分数。具体来说，在 8\（\times \） 超分辨率实验中，CelebA 数据集上的 PSNR/SSIM/LPIPS 为 27.68dB/ 0.8112/0.0866，在准确性和视觉质量方面都优于现有的最先进的方法。