Quaternion Generative Adversarial Neural Networks and Applications to Color Image Inpainting

TL;DR

This paper introduces a Quaternion GAN model that leverages channel correlation for improved color image inpainting, especially effective for large missing areas, outperforming existing methods.

Contribution

The paper proposes a novel Quaternion GAN architecture with quaternion deconvolution and batch normalization for better color image inpainting.

Findings

QGAN outperforms state-of-the-art algorithms in large-area color image inpainting

Quaternion modules improve stability and correlation utilization in the network

Experimental results demonstrate superior inpainting quality with QGAN

Abstract

Color image inpainting is a challenging task in imaging science. The existing method is based on real operation, and the red, green and blue channels of the color image are processed separately, ignoring the correlation between each channel. In order to make full use of the correlation between each channel, this paper proposes a Quaternion Generative Adversarial Neural Network (QGAN) model and related theory, and applies it to solve the problem of color image inpainting with large area missing. Firstly, the definition of quaternion deconvolution is given and the quaternion batch normalization is proposed. Secondly, the above two innovative modules are applied to generate adversarial networks to improve stability. Finally, QGAN is applied to color image inpainting and compared with other state-of-the-art algorithms. The experimental results show that QGAN has superiority in color image inpainting with large area missing.