TY - JOUR
T1 - Real-time data-driven interactive rough sketch inking
AU - Simo-Serra, Edgar
AU - Iizuka, Satoshi
AU - Ishikawa, Hiroshi
N1 - Funding Information:
This work was partially supported by JST CREST Grant Number JP-MJCR14D1, JST ACT-I Grant Number JPMJPR16UD, and JST ACT-I Grant Number JPMJPR16U3.
Publisher Copyright:
© 2018 Copyright held by the owner/author(s).
PY - 2018
Y1 - 2018
N2 - We present an interactive approach for inking, which is the process of turning a pencil rough sketch into a clean line drawing. The approach, which we call the Smart Inker, consists of several "smart" tools that intuitively react to user input, while guided by the input rough sketch, to efficiently and naturally connect lines, erase shading, and fine-tune the line drawing output. Our approach is data-driven: The tools are based on fully convolutional networks, which we train to exploit both the user edits and inaccurate rough sketch to produce accurate line drawings, allowing high-performance interactive editing in real-time on a variety of challenging rough sketch images. For the training of the tools, we developed two key techniques: One is the creation of training data by simulation of vague and quick user edits; the other is a line normalization based on learning from vector data. These techniques, in combination with our sketch-specific data augmentation, allow us to train the tools on heterogeneous data without actual user interaction. We validate our approach with an in-depth user study, comparing it with professional illustration software, and show that our approach is able to reduce inking time by a factor of 1.8×, while improving the results of amateur users.
AB - We present an interactive approach for inking, which is the process of turning a pencil rough sketch into a clean line drawing. The approach, which we call the Smart Inker, consists of several "smart" tools that intuitively react to user input, while guided by the input rough sketch, to efficiently and naturally connect lines, erase shading, and fine-tune the line drawing output. Our approach is data-driven: The tools are based on fully convolutional networks, which we train to exploit both the user edits and inaccurate rough sketch to produce accurate line drawings, allowing high-performance interactive editing in real-time on a variety of challenging rough sketch images. For the training of the tools, we developed two key techniques: One is the creation of training data by simulation of vague and quick user edits; the other is a line normalization based on learning from vector data. These techniques, in combination with our sketch-specific data augmentation, allow us to train the tools on heterogeneous data without actual user interaction. We validate our approach with an in-depth user study, comparing it with professional illustration software, and show that our approach is able to reduce inking time by a factor of 1.8×, while improving the results of amateur users.
KW - Iine drawing
KW - Inking
KW - Interaction
KW - Sketching
UR - http://www.scopus.com/inward/record.url?scp=85056735494&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85056735494&partnerID=8YFLogxK
U2 - 10.1145/3197517.3201370
DO - 10.1145/3197517.3201370
M3 - Article
AN - SCOPUS:85056735494
VL - 37
JO - ACM Transactions on Graphics
JF - ACM Transactions on Graphics
SN - 0730-0301
IS - 4
M1 - A59
ER -