...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on multimedia >Non-Local Texture Optimization With Wasserstein Regularization Under Convolutional Neural Network
【24h】

Non-Local Texture Optimization With Wasserstein Regularization Under Convolutional Neural Network

机译：卷积神经网络下具有Wasserstein正则化的非局部纹理优化

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Example-based texture synthesis aims to generate a new texture from an exemplar texture and has long been drawing attention in the fields of computer graphics, computer vision, and image processing. Nevertheless, synthesizing structured textures remains a challenging task. Most previous methods rely on additional guidance channels, which encode the structured features of textures. However, estimating the guidance channel is very difficult, and often fails when a texture has unpronounced features. In this paper, we propose a novel texture synthesis method, based on non-local operators, which captures the long-range structure of a texture without the additional guidance channel. The synthesized texture is generated by minimizing non-local texture energy through an expectation-maximization like optimization algorithm. A statistical constraint based on the Wasserstein distance is also proposed to ensure that the synthesized texture preserves the global statistics of the exemplar texture. Extensive experiments show that the proposed method can stably handle textures with different scale structures.
机译：基于示例的纹理合成旨在从示例纹理中生成新纹理，并且长期以来一直在计算机图形，计算机视觉和图像处理领域引起关注。尽管如此，合成结构化纹理仍然是一项艰巨的任务。先前的大多数方法都依赖于附加的引导通道，这些通道对纹理的结构化特征进行编码。但是，估计引导通道非常困难，并且当纹理具有非发音特征时通常会失败。在本文中，我们提出了一种基于非局部算子的新颖纹理合成方法，该方法无需额外的引导通道即可捕获纹理的远程结构。合成纹理是通过像期望算法那样的期望最大化最大化非局部纹理能量来生成的。还提出了基于Wasserstein距离的统计约束，以确保合成纹理保留示例纹理的全局统计信息。大量实验表明，该方法可以稳定地处理不同尺度结构的纹理。

著录项

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