arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.10333cs.CVcs.GR
收藏

神经轮廓:学习从3D模型中绘制线条

Neural Contours: Learning to Draw Lines from 3D Shapes

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Adobe Research(Adobe研究院)

Difan Liu, Mohamed Nabail, Aaron Hertzmann, Evangelos Kalogerakis

摘要:

本文介绍了一种学习从3D模型生成线条图的方法。我们的架构采用了可微模块操作的3D模型的几何特征,和基于图像的模块操作基于视图的形状表示。在测试时,几何和基于视图的推理与神经模块的帮助相结合,以创建线条画。该模型是在大量众包的线条图比较上训练的。实验表明,我们的方法实现了显着的改进,线条画在国家的最先进的标准基准评估时,产生的图纸是由经验丰富的人类艺术家制作的。

英文摘要:

This paper introduces a method for learning to generate line drawings from 3D models. Our architecture incorporates a differentiable module operating on geometric features of the 3D model, and an image-based module operating on view-based shape representations. At test time, geometric and view-based reasoning are combined with the help of a neural module to create a line drawing. The model is trained on a large number of crowdsourced comparisons of line drawings. Experiments demonstrate that our method achieves significant improvements in line drawing over the state-of-the-art when evaluated on standard benchmarks, resulting in drawings that are comparable to those produced by experienced human artists.

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。

↑