Combination of single image super resolution and digital Inpainting algorithms based on GANS for robust image completion

Hayrapetyan Sparik; Karapetyan Gevorg; Voronin Viacheslav; Sarukhanyan Hakob

首页> 外文期刊>Serbian Journal of Electrical Engineering >Combination of single image super resolution and digital Inpainting algorithms based on GANS for robust image completion

【24h】

Combination of single image super resolution and digital Inpainting algorithms based on GANS for robust image completion

机译：结合单图像超分辨率和基于GANS的数字修复算法，实现鲁棒的图像完成

获取原文

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Image inpainting, a technique of completing missing or corrupted image regions in undetected form, is an open problem in digital image processing. Inpainting of large regions using Deep Convolutional Generative Adversarial Nets (DCGAN) is a new and powerful approach. In described approaches the size of generated image and size of input image should be the same. In this paper we propose a new method where the size of input image with corrupted region can be up to 4 times larger than generated image.

机译：图像修补是一种以未检测到的形式完成缺失或损坏的图像区域的技术，是数字图像处理中的一个开放问题。使用深度卷积生成对抗网络（DCGAN）对大区域进行修补是一种新颖而强大的方法。在所描述的方法中，所生成图像的大小和输入图像的大小应该相同。在本文中，我们提出了一种新方法，其中具有损坏区域的输入图像的大小可以比生成的图像大4倍。

著录项

来源
《Serbian Journal of Electrical Engineering》 |2017年第3期|共8页
作者
Hayrapetyan Sparik; Karapetyan Gevorg; Voronin Viacheslav; Sarukhanyan Hakob;
展开▼
作者单位

展开▼
收录信息
原文格式 PDF
正文语种
中图分类电工技术;
关键词

相似文献

外文文献
中文文献
专利

1. A Concert Evaluation of Exemplar Based Image Inpainting Algorithms for Natural Scene Image Completion [J] . K.Sangeetha, P.Sengottuvelan, E.Balamurugan Computer Science & Information Technology . 2012,第4期

机译：基于样例的自然场景图像完成算法的协调评估
2. Robust deep learning-based multi-image super-resolution using inpainting [J] . Yau Henry, Du Xian Journal of electronic imaging . 2021,第1期

机译：基于深度学习的多图像超分辨率使用尿素
3. Extended Wavelet Transform Based Image Inpainting Algorithm for Natural Scene Image Completion [J] . K.Sangeetha, P.Sengottuvelan, E.Balamurugan Computer Science & Information Technology . 2012,第4期

机译：基于扩展小波变换的自然场景图像修补算法
4. Performance analysis of exemplar based image inpainting algorithms for natural scene image completion [C] . Sangeetha K., Sengottuvelan P., Balamurugan E. International Conference on Intelligent Systems and Control . 2013

机译：基于样例的自然场景图像完成算法的性能分析
5. Exploring the Internal Statistics: Single Image Super-Resolution, Completion and Captioning [D] . Xian, Yang. 2017

机译：探索内部统计信息：单图像超分辨率，完成和字幕
6. Feature Selection for Object-Based Classification of High-Resolution Remote Sensing Images Based on the Combination of a Genetic Algorithm and Tabu Search [O] . Lei Shi, Youchuan Wan, Xianjun Gao, 2018

机译：遗传算法与禁忌搜索相结合的高分辨率遥感影像基于对象分类的特征选择
7. Combined robust and fragile watermarking algorithms for still images. Design and evaluation of combined blind discrete wavelet transform-based robust watermarking algorithms for copyright protection using mobile phone numbers and fragile watermarking algorithms for content authentication of digital still images using hash functions. [O] . Jassim Taha Dawood 2014

机译：结合了鲁棒和脆弱的水印算法来处理静态图像。基于组合离散盲小波变换的鲁棒水印算法的设计和评估，该算法使用手机号码进行版权保护，使用脆弱的水印算法，使用哈希函数对数字静态图像进行内容认证。
8. High Resolution Bathymetry Estimation Improvement with Single ImageSuper Resolution Algorithm Super Resolution Forests. [R] . Einsidleg, D., Nock, K., Bonanno, D., 2017

机译：单图像超分辨率算法超分辨率森林高分辨率水深估算改进。

Combination of single image super resolution and digital Inpainting algorithms based on GANS for robust image completion

摘要

著录项

相似文献

相关主题

期刊订阅