SFI-Swin: Symmetric Face Inpainting with Swin Transformer by Distinctly Learning Face Components Distributions

TL;DR

This paper introduces SFI-Swin, a face inpainting method using Swin Transformer and multiple discriminators to better preserve symmetry and homogeneity, along with a new symmetry metric, outperforming existing models.

Contribution

The paper proposes a novel symmetric face inpainting approach with a transformer network, multiple discriminators for face components, and a new symmetry metric.

Findings

Outperforms recent algorithms in realism, symmetry, and homogeneity.

Uses multiple discriminators to evaluate face components separately.

Introduces a new symmetry concentration score for assessment.

Abstract

Image inpainting consists of filling holes or missing parts of an image. Inpainting face images with symmetric characteristics is more challenging than inpainting a natural scene. None of the powerful existing models can fill out the missing parts of an image while considering the symmetry and homogeneity of the picture. Moreover, the metrics that assess a repaired face image quality cannot measure the preservation of symmetry between the rebuilt and existing parts of a face. In this paper, we intend to solve the symmetry problem in the face inpainting task by using multiple discriminators that check each face organ's reality separately and a transformer-based network. We also propose "symmetry concentration score" as a new metric for measuring the symmetry of a repaired face image. The quantitative and qualitative results show the superiority of our proposed method compared to some of the recently proposed algorithms in terms of the reality, symmetry, and homogeneity of the inpainted parts.