arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.03057cs.CV
收藏

基于纹理合成的风格传递

Style-Transfer via Texture-Synthesis

Google Research(谷歌研究院)

Michael Elad, Peyman Milanfar

摘要:

风格转移是将一种风格从一幅图像迁移到另一幅图像的内容上,合成一幅新的图像的过程。最近采用卷积神经网络(CNN)在这个问题上的工作点燃了这个领域的新的兴趣,由于获得了非常令人印象深刻的结果。有一个替代的路径来处理风格转移的任务,通过纹理合成算法的泛化。这种方法已经提出了多年,但其结果通常不如CNN的令人印象深刻。在这项工作中,我们提出了一种新的风格转移算法,扩展了Kwatra等人的纹理合成工作。(2005),同时旨在获得风格化的图像,在质量上接近CNN的。我们修改Kwatra的算法在几个关键的方式,以实现所需的传输,重点是一个一致的方式保持内容完整的选定区域,而在其他人产生幻觉和丰富的风格。所获得的结果是视觉上令人愉快的和多样的,显示出与最近的CNN风格转移算法的竞争力。该算法快速灵活,能够处理任意一对内容+风格图像。

英文摘要:

Style-transfer is a process of migrating a style from a given image to the content of another, synthesizing a new image which is an artistic mixture of the two. Recent work on this problem adopting Convolutional Neural-networks (CNN) ignited a renewed interest in this field, due to the very impressive results obtained. There exists an alternative path towards handling the style-transfer task, via generalization of texture-synthesis algorithms. This approach has been proposed over the years, but its results are typically less impressive compared to the CNN ones. In this work we propose a novel style-transfer algorithm that extends the texture-synthesis work of Kwatra et. al. (2005), while aiming to get stylized images that get closer in quality to the CNN ones. We modify Kwatra's algorithm in several key ways in order to achieve the desired transfer, with emphasis on a consistent way for keeping the content intact in selected regions, while producing hallucinated and rich style in others. The results obtained are visually pleasing and diverse, shown to be competitive with the recent CNN style-transfer algorithms. The proposed algorithm is fast and flexible, being able to process any pair of content + style images.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑