Tool- and Domain-Agnostic Parameterization of Style Transfer Effects Leveraging Pretrained Perceptual Metrics
Tool- and Domain-Agnostic Parameterization of Style Transfer Effects Leveraging Pretrained Perceptual Metrics
复制标题
DOI：
10.24963/ijcai.2021/167
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Hiromu Yakura;Yuki Koyama;Masataka Goto
中科院分区：
文献类型：
--
作者：
Hiromu Yakura;Yuki Koyama;Masataka Goto
目前用于风格转换的深度学习技术对于设计支持来说不是最佳的，因为它们的“一次性”转换不适合探索性设计过程。为了克服这一差距，我们提出了参数转录，它转录到现有的内容编辑工具中可用的特定转换的参数值的端到端的风格转换效果。通过这种方法，用户可以在他们熟悉的工具中模仿参考样本的风格，从而可以通过操纵参数轻松地继续进一步探索。为了实现这一点，我们引入了一个框架，该框架利用现有的预训练模型进行风格转移来计算与参考样本的感知风格距离，并使用黑盒优化来找到最小化该距离的参数。我们使用各种第三方工具（如Instagram和Blender）进行的实验表明，我们的框架可以有效地利用深度学习技术来支持计算设计。
Current deep learning techniques for style transfer would not be optimal for design support since their "one-shot" transfer does not fit exploratory design processes. To overcome this gap, we propose parametric transcription, which transcribes an end-to-end style transfer effect into parameter values of specific transformations available in an existing content editing tool. With this approach, users can imitate the style of a reference sample in the tool that they are familiar with and thus can easily continue further exploration by manipulating the parameters. To enable this, we introduce a framework that utilizes an existing pretrained model for style transfer to calculate a perceptual style distance to the reference sample and uses black-box optimization to find the parameters that minimize this distance. Our experiments with various third-party tools, such as Instagram and Blender, show that our framework can effectively leverage deep learning techniques for computational design support.