Line Drawing Extraction from Cartoons Using a Conditional Generative Adversarial Network

Kyungho Yu,Hee-Deok Yang,Juhyeon Noh

doi:10.3390/app11167536

Abstract

Recently, three-dimensional (3D) content used in various fields has attracted attention owing to the development of virtual reality and augmented reality technologies. To produce 3D content, we need to model the objects as vertices. However, high-quality modeling is time-consuming and costly. Drawing-based modeling is a technique that shortens the time required for modeling. It refers to creating a 3D model based on a user’s line drawing, which is a 3D feature represented by two-dimensional (2D) lines. The extracted line drawing provides information about a 3D model in the 2D space. It is sometimes necessary to generate a line drawing from a 2D cartoon image to represent the 3D information of a 2D cartoon image. The extraction of consistent line drawings from 2D cartoons is difficult because the styles and techniques differ depending on the designer who produces the 2D cartoons. Therefore, it is necessary to extract line drawings that show the geometric characteristics well in 2D cartoon shapes of various styles. This paper proposes a method for automatically extracting line drawings. The 2D cartoon shading image and line drawings are learned using a conditional generative adversarial network model, which outputs the line drawings of the cartoon artwork. The experimental results show that the proposed method can obtain line drawings representing the 3D geometric characteristics with a 2D line when a 2D cartoon painting is used as the input.

Highlights

Content created using 3D computer graphics technology is used in various fields, such as games, movies, animation and education, because it allows users to experience a real-world environment with 3D content
The datasets used for the learning consisted of cartoon images (Figure 11a) and their corresponding line drawings (Figure 11b) created from 896 three-dimensional models
The line drawing used in the study consisted of a subdivision surface twice larger than that of the 3D model

Summary

Introduction

Content created using 3D (three-dimensional) computer graphics technology is used in various fields, such as games, movies, animation and education, because it allows users to experience a real-world environment with 3D content. The drawing-based modeling technique is commonly used to reduce the time required to perform 3D modeling This technique involves creating a 3D model based on line drawings or sketches [1,2,3,4]. Feature line extraction from a 2D cartoon image, such as Canny edge detection in a 2D cartoon image, is different from the characteristic lines generated according to the curvature of the 3D model or the relationship between each vertex and the viewpoint. As. Feature line extraction from a 2D cartoon image, such as Canny edge detection in a 2D cartoon image, is different from the characteristic lines generated according to the curcavbneatsbueereensoeifentnhFeiing3uDFriemg1uoard,eethl1eoar,fetthhateeurrfeeelaaltitnuioernsesehlxiintpreabscetetewxdterfearnoctmeeadcthhfervo2emDrtectxhareatno2doDnthciemavratigoeewondpooiminnoat.tgAreespdcroaen-not respenretstehnet gtheoemgeetormic eptrroicpperrtoiepseortfiethseof3Dthem3oDdeml. ThTeheppuurprpooseseoofftthhiissppaappeerr iiss ttoo eexxttrraacctt33DDffeeaatuturerelilnineessfrformoma a2D2Dcacratortoonoinmiamgae,gaes, ashsoswhonwn ininFiFgiguurere11cc. Sci. 2021, 11, x FOR PEER REVIEW representation in esthetic and realistic depictions. Q(s) is a vector of the tangent planes that indicates how the normal vectors change as they move along vector s on the screen

Autoencoder

Line Drawing Extraction from a 2D Cartoon Image

Generative Adversarial Network

Conditional Generative Adversarial Network

Experimental Results and Analysis

Conclusions and Further