Open Access

ARTICLE

Spatial and Contextual Path Network for Image Inpainting

Dengyong Zhang^1,2, Yuting Zhao^1,2, Feng Li^1,2, Arun Kumar Sangaiah^3,4,*

1 Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation, Changsha University of Science and Technology, Changsha, 410114, China
2 School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, 410114, China
3 International Graduate Institute of AI, National Yunlin University of Science and Technology, Yunlin, Taiwan
4 Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon

* Corresponding Author: Arun Kumar Sangaiah. Email:

(This article belongs to the Special Issue: Explainable Artificial Intelligence (XAI): Methodologies, Interactivity and Applications)

Intelligent Automation & Soft Computing 2024, 39(2), 115-133. https://doi.org/10.32604/iasc.2024.040847

Received 01 April 2023; Accepted 31 January 2024; Issue published 21 May 2024

Abstract

Image inpainting is a kind of use known area of information technology to repair the loss or damage to the area. Image feature extraction is the core of image restoration. Getting enough space for information and a larger receptive field is very important to realize high-precision image inpainting. However, in the process of feature extraction, it is difficult to meet the two requirements of obtaining sufficient spatial information and large receptive fields at the same time. In order to obtain more spatial information and a larger receptive field at the same time, we put forward a kind of image restoration based on space path and context path network. For the space path, we stack three convolution layers for 1/8 of the figure, the figure retained the rich spatial details. For the context path, we use the global average pooling layer, where the accept field is the maximum of the backbone network, and the pooling module can provide global context information for the maximum accept field. In order to better integrate the features extracted from the spatial and contextual paths, we study the fusion module of the two paths. Features fusion module first path output of the space and context path, and then through the mass normalization to balance the scale of the characteristics, finally the characteristics of the pool will be connected into a feature vector and calculate the weight vector. Features of images in order to extract context information, we add attention to the context path refinement module. Attention modules respectively from channel dimension and space dimension to weighted images, in order to obtain more effective information. Experiments show that our method is better than the existing technology in the quality and quantity of the method, and further to expand our network to other inpainting networks, in order to achieve consistent performance improvements.

---

Keywords

---