arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.11958cs.LGstat.ML
收藏

StrokeCoder:使用Transformers从单个示例生成基于路径的图像

StrokeCoder: Path-Based Image Generation from Single Examples using Transformers

Institute for Neural Information Processing(神经信息处理研究所);Ulm University(乌尔姆大学)

Sabine Wieluch, Friedhelm Schwenker

摘要:

本文演示了如何使用Transformer神经网络从基于单个路径的示例图像学习生成模型。我们进一步展示了如何从示例图像生成数据集,以及如何使用该模型生成大量偏离图像,这些图像仍然代表原始图像的风格和概念。

英文摘要:

This paper demonstrates how a Transformer Neural Network can be used to learn a Generative Model from a single path-based example image. We further show how a data set can be generated from the example image and how the model can be used to generate a large set of deviated images, which still represent the original image's style and concept.

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。

↑