Close-up facial images captured at short distances often suffer from perspective distortion, resulting in exaggerated facial features and unnatural/unattractive appearances. We propose a simple yet effective method for correcting perspective distortions in a single close-up face. We first perform GAN inversion using a perspective-distorted input facial image by jointly optimizing the camera intrinsic/extrinsic parameters and face latent code. To address the ambiguity of joint optimization, we develop starting from a short distance, optimization scheduling, reparametrizations, and geometric regularization. Re-rendering the portrait at a proper focal length and camera distance effectively corrects perspective distortions and produces more natural-looking results. Our experiments show that our method compares favorably against previous approaches qualitatively and quantitatively. We showcase numerous examples validating the applicability of our method on in-the-wild portrait photos. We will release our code and the evaluation protocol to facilitate future work.

翻译：短距离拍摄的近距离人脸图像常受透视畸变影响，导致面部特征夸张及不自然/不美观的外观。我们提出一种针对单张近距离人像进行透视畸变校正的简单有效方法。首先，通过联合优化相机内参/外参及人脸隐码，利用透视畸变输入人脸图像进行GAN反演。为解决联合优化的歧义性，我们开发了从短距离起始的优化策略、调度机制、重参数化方法及几何正则化技术。在适当焦距和相机距离下重新渲染人像，可有效校正透视畸变并生成更自然的结果。实验表明，我们的方法在定性和定量上均优于现有方法。我们通过大量示例验证了该方法在自然场景人像照片上的适用性。将公开代码与评估协议以促进后续研究。