DNNAM: Image inpainting algorithm via deep neural networks and attention mechanism

• Published in: Applied soft computing Vol. 154; p. 111392
• Main Authors: Chen, Yuantao, Xia, Runlong, Yang, Kai, Zou, Ke
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.03.2024
• Subjects: Attention Mechanism; Deep Neural Networks; Image Inpainting; Partial Multi-scale Channel; Residual Network; Image Inpainting; Deep Neural Networks; Partial Multi-scale Channel; Residual Network; Attention Mechanism
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2024.111392

Most image inpainting algorithms have problems such as fuzzy images, texture distortion and semantic inaccuracy, and the image inpainting effect is limited when processing photos with large missing sections and resolution levels. The paper proposes an effective image inpainting algorithm via partial multi-scale channel attention mechanism and deep neural networks to address the above phenomenon that existing image inpainting methods using deep learning modules have insufficient perception and representation capabilities for multi-scale features with high proportion of irregular defects. Initially, we used the Res-U-Net module as a generator. The U-Net-like backbone network topology can achieve the encoding and decoding stages of damaged images. Secondly, the residual network structure was built in the encoder and decoder to improve the ability of the proposed network to extract and display the features of the damaged images. Finally, the partial multi-scale channel attention module was inserted in the skip connection with the decoder to increase the efficiency of using the low-level features of the original images. The experimental results of the research can show that the proposed method outperforms state-of-the-art methods in terms of subjective visual perception and objective evaluation indicators on the CelebA, Places2 and Paris Street View datasets. •The model has improved the ability to extract and express multi-scale features.•The method had included partial multi-scale channel attention and residual network.•The backbone network structure can realize encoding and decoding stage.•The structure of residual networks had constructed to enhance the abilities.