Learning to Trace: Expressive Line Drawing Generation from Photographs. (14th November 2019)
- Record Type:
- Journal Article
- Title:
- Learning to Trace: Expressive Line Drawing Generation from Photographs. (14th November 2019)
- Main Title:
- Learning to Trace: Expressive Line Drawing Generation from Photographs
- Authors:
- Inoue, N.
Ito, D.
Xu, N.
Yang, J.
Price, B.
Yamasaki, T. - Abstract:
- Abstract: In this paper, we present a new computational method for automatically tracing high‐resolution photographs to create expressive line drawings. We define expressive lines as those that convey important edges, shape contours, and large‐scale texture lines that are necessary to accurately depict the overall structure of objects (similar to those found in technical drawings) while still being sparse and artistically pleasing. Given a photograph, our algorithm extracts expressive edges and creates a clean line drawing using a convolutional neural network (CNN). We employ an end‐to‐end trainable fully‐convolutional CNN to learn the model in a data‐driven manner. The model consists of two networks to cope with two sub‐tasks; extracting coarse lines and refining them to be more clean and expressive. To build a model that is optimal for each domain, we construct two new datasets for face/body and manga background. The experimental results qualitatively and quantitatively demonstrate the effectiveness of our model. We further illustrate two practical applications.
- Is Part Of:
- Computer graphics forum. Volume 38:Number 7(2019)
- Journal:
- Computer graphics forum
- Issue:
- Volume 38:Number 7(2019)
- Issue Display:
- Volume 38, Issue 7 (2019)
- Year:
- 2019
- Volume:
- 38
- Issue:
- 7
- Issue Sort Value:
- 2019-0038-0007-0000
- Page Start:
- 69
- Page End:
- 80
- Publication Date:
- 2019-11-14
- Subjects:
- CCS Concepts -- Computing methodologies → Image manipulation -- Applied computing → Fine arts
Computer graphics -- Periodicals
006.605 - Journal URLs:
- http://onlinelibrary.wiley.com/doi/10.1111/j.1467-8659.1982.tb00001.x/abstract ↗
http://onlinelibrary.wiley.com/ ↗
http://www.blackwell-synergy.com/servlet/useragent?func=showIssues&code=cgf ↗ - DOI:
- 10.1111/cgf.13817 ↗
- Languages:
- English
- ISSNs:
- 0167-7055
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3393.982000
British Library DSC - BLDSS-3PM
British Library STI - ELD Digital store - Ingest File:
- 21501.xml