首页> 外文会议>Chinese Control Conference >Neural Style Transfer for Picture with Gradient Gram Matrix Description
【24h】

Neural Style Transfer for Picture with Gradient Gram Matrix Description

机译:带有梯度革兰矩阵描述的图片的神经样式传递

获取原文

摘要

Despite the high performance of neural style transfer on stylized pictures, we found that Gatys et al [1] algorithm cannot perfectly reconstruct texture style. Output stylized picture could emerge unsatisfied unexpected textures such like muddiness in local area and insufficient grain expression. Our method bases on original algorithm, adding the Gradient Gram description on style loss, aiming to strengthen texture expression and eliminate muddiness. To some extent our method lengthens the runtime, however, its output stylized pictures get higher performance on texture details, especially in the elimination of muddiness.
机译:尽管在样式化图片上神经样式转移具有高性能,但我们发现Gatys等人[1]算法无法完美地重建纹理样式。输出的风格化图片可能会出现不满意的意外纹理,例如局部浑浊和纹理表达不足。我们的方法基于原始算法,在样式损失上添加了梯度革描述,旨在增强纹理表达并消除浑浊。我们的方法在某种程度上延长了运行时间,但是,其输出的风格化图片在纹理细节方面表现出更高的性能,尤其是在消除泥泞感方面。

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