arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.16441cs.CV
收藏

交互式神经绘画

Interactive Neural Painting

University of Trento(特伦托大学);Picsart AI Research (PAIR)(Picsart人工智能研究院(PAIR));Politecnico di Milano(米兰理工大学);ETZ;University of Illinois Urbana Champaign (UIUC)(伊利诺伊大学厄巴纳-香槟分校(UIUC));Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会)

Elia Peruzzo, Willi Menapace, Vidit Goel, Federica Arrigoni, Hao Tang, Xingqian Xu, Arman Chopikyan, Nikita Orlov, Yuxiao Hu, Humphrey Shi, Nicu Sebe, Elisa Ricci

AI总结:

本文提出首个交互式神经绘画方法I-Paint,基于条件Transformer VAE架构,通过建议笔画辅助用户创作,并引入两个新数据集,实验验证其效果优于现有方法。

摘要:

近年来,神经绘画(NP)技术已能够生成极其逼真的艺术作品。本文通过提出首个交互式神经绘画(Interactive NP)方法,推动了这一新兴研究领域的发展。考虑到用户观察场景并尝试在画布上重现它的场景,我们的目标是开发一个计算框架,通过建议接下来可以绘制的笔画来辅助用户的创造力,这些笔画可能用于完成艺术品。为实现这一任务,我们提出了I-Paint,一种基于条件Transformer变分自编码器(VAE)架构并带有两阶段解码器的新方法。为了评估所提出的方法并促进该领域的研究,我们还引入了两个新数据集。我们的实验表明,我们的方法提供了良好的笔画建议,并且与最先进的方法相比表现更优。更多细节、代码和示例可在https://helia95.github.io/inp-website获取。

英文摘要:

In the last few years, Neural Painting (NP) techniques became capable of producing extremely realistic artworks. This paper advances the state of the art in this emerging research domain by proposing the first approach for Interactive NP. Considering a setting where a user looks at a scene and tries to reproduce it on a painting, our objective is to develop a computational framework to assist the users creativity by suggesting the next strokes to paint, that can be possibly used to complete the artwork. To accomplish such a task, we propose I-Paint, a novel method based on a conditional transformer Variational AutoEncoder (VAE) architecture with a two-stage decoder. To evaluate the proposed approach and stimulate research in this area, we also introduce two novel datasets. Our experiments show that our approach provides good stroke suggestions and compares favorably to the state of the art. Additional details, code and examples are available at https://helia95.github.io/inp-website.

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。

↑