基于多粒度特征融合的边缘一致性图像补全
作者:
作者单位:

重庆邮电大学

作者简介:

通讯作者:

中图分类号:

TP391

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)


Edge Consistent Image Completion Based on Multi-granularity Feature Fusion
Author:
Affiliation:

Chongqing University of Posts and Telecommunications

Fund Project:

The National Natural Science Foundation of China (General Program, Key Program, Major Research Plan)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    图像补全是数字图像处理领域的一项重要研究内容,大面积不规则缺失图像的补全是近年来的研究热点.然而,现有的图像补全技术存在一些局限性,基于生成式对抗网络的方法忽略了图像的边缘结构信息,存在无法还原精细细节的问题;基于局部判别器的方法不能处理非矩形的缺失图像,存在补全任务不符合实际应用场景的问题;等等.本文结合多粒度认知计算的思想,提出了基于多粒度特征融合的边缘判别器,充分学习不同粒度的边缘结构信息,提高生成图像边缘和真实图像边缘的一致性,生成结构更加清晰的补全图像.同时,提出了边缘空间衰减损失,提高边缘区域像素的连续性.此外,利用注意力机制将补全区域的像素作为有效像素,优化局部判别器使其能够处理非矩形缺失图像.在Places2和Paris Streetview等公共数据集上的实验结果表明,在补全大面积不规则缺失图像时,本文方法取得了比其他图像补全方法更好的效果,在一定程度上说明了边缘结构信息在图像补全研究中的重要性.

    Abstract:

    Image completion is an important research content in the field of digital image processing, and the completion of large area irregular missing images is a research hotspot in recent years. However, the existing image completion technology has some limitations. The method based on generative adversarial network ignores the edge structure information of the image, and it can"t restore the fine details. The method based on local discriminator can"t deal with the missing irregular image, and the completion task doesn"t conform to the actual application scene. Combined with the idea of multi- granularity cognitive computing, this paper proposes an edge discriminator based on multi-granularity feature fusion, which can fully learn the edge structure information of different granularity, improve the consistency between the generated image edge and the real image edge, and generate the complete image with clearer structure. At the same time, the edge space attenuation loss is proposed to improve the continuity of pixels in the edge region. In addition, the attention mechanism is used to optimize the local discriminator to process the irregular missing image. Experimental results on Places2, Paris Streetview and other public datasets show that the proposed method achieves better results than other image completion methods in the completion of large areas of irregular missing images, which illustrates the importance of edge structure information in image completion research to a certain extent.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-04-19
  • 最后修改日期:2021-08-25
  • 录用日期:2021-08-26
  • 在线发布日期: 2021-09-17
  • 出版日期: