DisCO：使用透视感知 3D GAN 进行人像畸变校正
DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs
AI总结：
针对近距离特写入脸的透视畸变问题，本文提出 DisCO，通过透视感知 3D GAN inversion 联合优化相机参数与潜码，并引入调度和几何正则化，实现自然的人像校正。
摘要：
在短距离拍摄的特写人脸图像通常会受到透视畸变的影响，导致面部特征被夸大，并呈现不自然或不美观的外观。我们提出了一种简单而有效的方法，用于校正单张特写入脸中的透视畸变。我们首先利用发生透视畸变的输入人脸图像执行 GAN inversion，通过联合优化相机内参/外参和人脸潜码来实现。为解决联合优化的模糊性，我们开发了从短距离开始、优化调度、重参数化以及几何正则化等策略。在合适的焦距和相机距离下重新渲染人像，可有效校正透视畸变，并产生看起来更自然的结果。实验表明，我们的方法在定性和定量方面均优于以往方法。我们展示了大量示例，验证了该方法在 in-the-wild 人像照片上的适用性。我们将发布代码和评估协议，以促进未来研究。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
