PCNet: partial convolution attention mechanism for image inpainting

Abstract

Image inpainting is an essential issue in the field of computer vision. The basic purpose is to automatically recover the lost content according to the known content in the image. Although significant progress has been made in the completion of the regular missing image, the completion of the irregular image is still challenging. The completed images generated by the previous methods were different from the surrounding areas, considering the low efficiency of convolution in processing spatial position information. Based on this study, a partial convolution attention mechanism for image inpainting was proposed (PCNet), and an attention mechanism was introduced to extract long-distance and irregular image content which is a self-supervised module capable of focusing on global information. In addition, attentive normalization is introduced to model the long-distance relationship on the conditional image generation task. Experiments show that the results generated by our method are more natural and real, and the completed parts demonstrate more connected consistency.

KEYWORDS:

• Partial convolution
• attention mechanism
• image inpainting

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Shiliang Yan

Shiliang Yan is the associate professor in Engineering and Technology Center, Southwest University of Science and Technology. He received an MS degree in control engineering in 2010 from Southwest University of Science and Technology, Mianyang, China. Currently, He is pursuing PhD degree from University of Electronic Science and Technology, Chengdu, China. His research includes are pattern recognition, image processing and deep learning.

Xiaofeng Zhang

Xiaofeng Zhang is pursuing his MS degree in 2018 from Nanjing university of posts and telecommunications, Nanjing, China. His research interests are machine intelligence and image understanding.