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

## TL;DR

This paper introduces DisCO, a perspective-aware 3D GAN-based method that corrects facial perspective distortions in close-up images by jointly optimizing camera parameters and face features, producing natural results.

## Contribution

The paper presents a novel approach combining GAN inversion with joint camera and face optimization to correct perspective distortions in a single image.

## Key findings

- Outperforms previous methods qualitatively and quantitatively
- Effectively corrects perspective distortions in in-the-wild portraits
- Produces more natural-looking facial images after correction

## Abstract

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.