arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.07238cs.CV
收藏

为图像生成和编辑建模艺术工作流

Modeling Artistic Workflows for Image Generation and Editing

University of California, Merced(加利福尼亚大学默塞德分校);Adobe Research(Adobe研究院)

Hung-Yu Tseng, Matthew Fisher, Jingwan Lu, Yijun Li, Vladimir Kim, Ming-Hsuan Yang

摘要:

人们通常通过遵循涉及多个阶段的艺术工作流程来创作艺术,这些阶段为整体设计提供信息。如果艺术家希望修改先前的决定,可能需要大量的工作来将这个新的决定传播到最终的艺术作品中。受上述观察的启发,我们提出了一个生成模型,该模型遵循给定的艺术工作流程,实现了现有艺术品的多阶段图像生成和多阶段图像编辑。此外,对于编辑场景,我们引入了优化过程以及基于学习的正则化,以确保模型生成的编辑图像与原始提供的图像紧密对齐。三个不同的艺术数据集上的定性和定量结果表明,所提出的框架对图像生成和编辑任务的有效性。

英文摘要:

People often create art by following an artistic workflow involving multiple stages that inform the overall design. If an artist wishes to modify an earlier decision, significant work may be required to propagate this new decision forward to the final artwork. Motivated by the above observations, we propose a generative model that follows a given artistic workflow, enabling both multi-stage image generation as well as multi-stage image editing of an existing piece of art. Furthermore, for the editing scenario, we introduce an optimization process along with learning-based regularization to ensure the edited image produced by the model closely aligns with the originally provided image. Qualitative and quantitative results on three different artistic datasets demonstrate the effectiveness of the proposed framework on both image generation and editing tasks.

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。

↑