Download pdf
Research on image inpainting methods based on machine learning
- 1 Dalian Neusoft University of Information
- 2 Dalian Maritime University
* Author to whom correspondence should be addressed.
Abstract
The technique of restoring sections of a picture that have been lost or damaged is known as "image inpainting." In light of recent developments in machine learning, academics have begun investigating the possibility of using deep learning methods to the process of picture inpainting. However, the current body of research does not include a comprehensive review of the many different inpainting methods that are based on machine learning, nor does it compare and contrast these methods. This article provides an overview of some of the most advanced and common machine learning based image restoration techniques that are currently available. These techniques include Multivariate inpainting technology and Unit inpainting technology, such as Context-Encoder Network, Generative Adversarial Network (GAN), and U-Net Network. We examine not just the benefits and drawbacks of each method, but also the ways in which it might be used in a variety of settings. At the conclusion of the piece, we predict that machine learning-based inpainting will continue to gain popularity and application in the years to come.
Keywords
image inpainting, machine learning, unit inpainting, multivariate inpainting
[1]. Pathak D, Kr Å Henb, etc. Context Encoder: Feature Learning Through Repair, 2016 IEEE Conf. Comp. Vis. Patt. Recog., 2536-2544.
[2]. Rumelhart D E, Hinton G E, Willims R J. Learning internal representations through error propagation. Univ. California, San Diego, 1985.
[3]. Liao L, Hu R, Xiao J, etc. Edge Aware Context Encoder for inpainting. 2018 Conf. Aco., Sp. Sig. Proc., 3156-3160.
[4]. Yang J, Qi Z, Shi Y. Learn to incorporate structural knowledge into inpainting. 2020, AAAI Artif. Intel. 12605-12612.
[5]. Wang Y, Tao X, Qi X, et al. inpainting by generating multi column convolutional neural networks, 2018 Annual Conf. Neur. Infor. Proc. Sys., 329-338.
[6]. Vo H V, Duong N K, P É Rez P. Structural Repair, 2018 ACM Inter. Mul. Conf., 1948 1956.
[7]. Ji L A region segmentation method based on full resolution attention U-Net neural network, 2023 Rad. Engin. 1-9
[8]. Wang W. Repair algorithm based on U-Net network and its application in Yi language restoration Yunnan Univ., 2021.
[9]. Liu Liqi, Liu Yanli. Load inpainting: an improved U-Net based load missing data recovery method. 2022 Applied Energy, 327.
[10]. Goodfellow I, Mirza M, etc. Generating adversarial networks, 2014 Annual Conf. Neur. Infor. Proc. Sys., 2672-2680.
[11]. Mirza M, Osidero S. Conditionally generated adversarial networks. ArXiv preprint arXiv: 1141.17842014.
[12]. Dolhansky B, Canton Ferrer C. Using Examples to Generate Eyes for Adversarial Network Painting 2018IEEE Conf. Comp. Vis. Patt. Recog.: 7902-7911.
[13]. Radford A, Metz L, Chintala S. Use deep convolution to generate adversarial networks for unsupervised representation learning. ArXiv preprint arXiv: 151106434015.
[14]. Han X, Wu Z, Huang W, et al. FiNet: Compatible and diversified fashion inpainting, 2019 Inter. Comp. Vis. Conf., 4480-4490.
[15]. Dupont E, Suresha S. Probabilistic Semantic Repair Using Pixel Constrained Cellular Neural Networks, 2019 Inter. Conf. Artif. Intel. Stat., 2261-2270.
[16]. Zhao L, Mo Q, Lin S, et al. UCTGAN: Diversified inpainting based on unsupervised cross space translation, 2020, IEEE Conf. Comp. Vis. Patt. Recog. 5740-5749.
[17]. Vaswani A, Shazeer N, Parmar N, etc. Attention is what you need. 2017 Annual Conf. Neur. Infor. Proc. Sys., 5998-6008.
[18]. Yu Yi, Zhan Fang, Wu Rong, et al. Diversity inpainting based on bidirectional and autoregressive transformations 2021, ACM Inter. Multi. Conf., 69-78.
[19]. Wan Z, Zhang J, Chen D, et al. Using Transformers to Achieve High Precision Multivariate Image Mosaic, 2021 Inter. Conf. Comp. Vis.,4672-4681.
Cite this article
Liu,Z.;Qin,M. (2023). Research on image inpainting methods based on machine learning. Applied and Computational Engineering,19,67-74.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 5th International Conference on Computing and Data Science
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).