Stylized line drawing of 3D models using CNN

被引：1

作者：

Uchida, Mitsuhiro ^{[1
]}

Saito, Suguru ^{[1
]}

机构：

[1] Tokyo Inst Technol, Sch Comp, Tokyo, Japan

来源：

2019 INTERNATIONAL CONFERENCE ON CYBERWORLDS (CW) | 2019年

关键词：

non-photorealistic rendering; line-drawing; convolutional neural network;

D O I：

10.1109/CW.2019.00015

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

Techniques to render 3D models like hand-drawings are often required. In this paper, we propose an approach that generates line-drawing with various styles by machine learning. We train two Convolutional neural networks (CNNs), of which one is a line extractor from the depth and normal images of a 3D object, and the other is a line thickness applicator. The following process to CNNs interprets the thickness of the lines as intensity to control properties of a line style. Using the obtained intensity, non-uniform line styled drawings are generated. The results show the efficiency of combining the machine learning method and the interpreter.

引用

页码：37 / 44

页数：8