Facial Expression Restoration Based on Improved Graph Convolutional Networks

TL;DR

This paper introduces a novel facial expression restoration method using an improved graph convolutional network integrated with a region relation modeling block, enhancing facial expression recovery in low-quality images.

Contribution

It proposes an IGCN that processes face patches as tensors and a RRMB for better facial expression restoration, addressing inpainting and super-resolution tasks.

Findings

Effective in restoring facial expressions in low-resolution images

Outperforms existing methods on BP4D and DISFA benchmarks

Improves facial action units detection accuracy

Abstract

Facial expression analysis in the wild is challenging when the facial image is with low resolution or partial occlusion. Considering the correlations among different facial local regions under different facial expressions, this paper proposes a novel facial expression restoration method based on generative adversarial network by integrating an improved graph convolutional network (IGCN) and region relation modeling block (RRMB). Unlike conventional graph convolutional networks taking vectors as input features, IGCN can use tensors of face patches as inputs. It is better to retain the structure information of face patches. The proposed RRMB is designed to address facial generative tasks including inpainting and super-resolution with facial action units detection, which aims to restore facial expression as the ground-truth. Extensive experiments conducted on BP4D and DISFA benchmarks demonstrate the effectiveness of our proposed method through quantitative and qualitative evaluations.