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 2012.02996cs.HC
收藏

绘画材料(MIP):感知、艺术史和计算机视觉的跨学科数据集

Materials In Paintings (MIP): An interdisciplinary dataset for perception, art history, and computer vision

Mitchell J. P. van Zuijlen, Hubert Lin, Kavita Bala, Sylvia C. Pont, Maarten W. A. Wijntjes

摘要:

画家可以自由地修改自然场景的组成部分,这可以导致远端世界的感知令人信服的图像。这标志着照片和绘画之间的一个主要区别:绘画是明确为人类感知而创作的。研究这些绘画技巧对多学科的观众可能是有益的。在这篇论文中,我们捕捉并探索材料的绘画性表现,使我们能够通过艺术家的眼睛来研究材料的描绘和感知。我们用200k+边界框注释了19k幅画的数据集,从中自动提取多边形段。每个限界框被分配粗略标签(例如,织物)和细粒标签(例如,天鹅绒般的、丝滑的)。我们展示了我们的数据集的跨学科的效用,提出了新的发现跨越艺术史,人类感知和计算机视觉。我们的实验包括分析绘画中描绘的材料的分布,展示画家如何使用程式化的方法创建令人信服的插图,并演示如何使用绘画来构建更强大的计算机视觉模型。我们的结论是,我们的绘画材料描述数据集是一个丰富的来源,可以深入了解跨多个学科的材料描述和感知。MIP数据集可在https://materialsinpaintings.tudelft.nl上免费访问

英文摘要:

A painter is free to modify how components of a natural scene are depicted, which can lead to a perceptually convincing image of the distal world. This signals a major difference between photos and paintings: paintings are explicitly created for human perception. Studying these painterly depictions could be beneficial to a multidisciplinary audience. In this paper, we capture and explore the painterly depictions of materials to enable the study of depiction and perception of materials through the artists' eye. We annotated a dataset of 19k paintings with 200k+ bounding boxes from which polygon segments were automatically extracted. Each bounding box was assigned a coarse label (e.g., fabric) and a fine-grained label (e.g., velvety, silky). We demonstrate the cross-disciplinary utility of our dataset by presenting novel findings across art history, human perception, and computer vision. Our experiments include analyzing the distribution of materials depicted in paintings, showing how painters create convincing depictions using a stylized approach, and demonstrating how paintings can be used to build more robust computer vision models. We conclude that our dataset of painterly material depictions is a rich source for gaining insights into the depiction and perception of materials across multiple disciplines. The MIP dataset is freely accessible at https://materialsinpaintings.tudelft.nl

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。

↑