DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs
This addresses the problem of unnatural appearances in portrait photos for photographers and users, but it is incremental as it builds on existing GAN inversion techniques.
The paper tackles perspective distortion in close-up facial images by jointly optimizing camera parameters and face latent codes with a 3D GAN, resulting in more natural-looking portraits with favorable qualitative and quantitative comparisons to previous methods.
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.