DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs

Zhixiang Wang, Yu-Lun Liu, Jia-Bin Huang, Shin'ichi Satoh, Sizhuo Ma, Guru Krishnan, Jian Wang

The University of Tokyo & National Institute of Informatics  & National Yang Ming Chiao Tung University & University of Maryland &  Snap Inc

DisCO：使用透视感知 3D GAN 进行人像失真校正
要点：
1.在近距离拍摄的特写面部图像通常会出现透视失真，导致夸张的面部特征和不自然/不吸引人的外观。

2.文章提出了一种简单而有效的方法来校正单个特写脸部中的透视失真。

3.首先通过联合优化相机内部/外部参数和面部潜在代码，使用透视扭曲的输入面部图像执行 GAN 反演。

4.为了解决联合优化的模糊性，开发了焦距重新参数化、优化调度和几何正则化。 以适当的焦距和相机距离重新渲染肖像可以有效地纠正这些失真并产生更自然的效果。

一句话总结：

实验表明，该方法在视觉质量方面优于以前的方法。 我们展示了许多示例，以验证我们的方法在野外人像照片上的适用性。[机器翻译+人工校对]

Close-up facial images captured at close 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 focal length reparametrization, optimization scheduling, and geometric regularization. Re-rendering the portrait at a proper focal length and camera distance effectively corrects these distortions and produces more natural-looking results. Our experiments show that our method compares favorably against previous approaches regarding visual quality. We showcase numerous examples validating the applicability of our method on portrait photos in the wild.

https://arxiv.org/pdf/2302.12253.pdf

内容中包含的图片若涉及版权问题，请及时与我们联系删除