...
首页> 外文期刊>Computer vision and image understanding >MTRNet++: One-stage mask-based scene text eraser
【24h】

MTRNet++: One-stage mask-based scene text eraser

机译:MTRNET ++:基于一级掩码的场景文本橡皮擦

获取原文
获取原文并翻译 | 示例
           

摘要

A precise, controllable, interpretable and easily trainable text removal approach is necessary for both user-specific and large-scale text removal applications.To achieve this, we propose a one-stage mask-based text inpainting network, MTRNet++.It has a novel architecture that includes mask-refine, coarse-inpainting and fine-inpainting branches, and attention blocks.With this architecture, MTRNet++ can remove text either with or without an external mask.It achieves state-of-the-art results on both the Oxford and SCUT datasets without using external ground-truth masks.The results of ablation studies demonstrate that the proposed multi-branch architecture with attention blocks is effective and essential.It also demonstrates controllability and interpretability.
机译:对于用户特定和大规模文本删除应用程序来说,需要精确,可控的,可解释和易于培训的文本拆除方法。要实现这一目标,我们提出了一个基于一个基于屏蔽的文本修复网络,MTRNET ++。它有一个小说包括掩模 - 精炼,粗污染和细小的分支的架构,以及注意力块。在此架构中,Mtrnet ++可以在或没有外部Mask的情况下删除文本。它可以在牛津上实现最先进的结果和SCUT数据集不使用外地实际掩模。消融研究结果表明,具有注意力块的提议的多分支架构是有效的,并且还表明了可控性和可解释性。

著录项

  • 来源
    《Computer vision and image understanding》 |2020年第12期|103066.1-103066.10|共10页
  • 作者单位

    Signal Processing Artificial Intelligence and Vision Technologies (SAIVT) Queensland University of Technology Australia;

    Signal Processing Artificial Intelligence and Vision Technologies (SAIVT) Queensland University of Technology Australia;

    Signal Processing Artificial Intelligence and Vision Technologies (SAIVT) Queensland University of Technology Australia Brain and Mind Centre The University of Sydney Australia;

    Signal Processing Artificial Intelligence and Vision Technologies (SAIVT) Queensland University of Technology Australia;

    Signal Processing Artificial Intelligence and Vision Technologies (SAIVT) Queensland University of Technology Australia;

    Signal Processing Artificial Intelligence and Vision Technologies (SAIVT) Queensland University of Technology Australia;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Image inpainting; Text removal; Generative adversarial network; Text detection; Inpainting;

    机译:图像染色;删除文本;生成对抗性网络;文本检测;in;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号