Joint gap detection and inpainting of line drawings

Kazuma Sasaki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa

研究成果: Conference contribution

14 被引用数 (Scopus)

抄録

We propose a novel data-driven approach for automatically detecting and completing gaps in line drawings with a Convolutional Neural Network. In the case of existing inpainting approaches for natural images, masks indicating the missing regions are generally required as input. Here, we show that line drawings have enough structures that can be learned by the CNN to allow automatic detection and completion of the gaps without any such input. Thus, our method can find the gaps in line drawings and complete them without user interaction. Furthermore, the completion realistically conserves thickness and curvature of the line segments. All the necessary heuristics for such realistic line completion are learned naturally from a dataset of line drawings, where various patterns of line completion are generated on the fly as training pairs to improve the model generalization. We evaluate our method qualitatively on a diverse set of challenging line drawings and also provide quantitative results with a user study, where it significantly outperforms the state of the art.

本文言語English
ホスト出版物のタイトルProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
出版社Institute of Electrical and Electronics Engineers Inc.
ページ5768-5776
ページ数9
ISBN(電子版)9781538604571
DOI
出版ステータスPublished - 2017 11 6
イベント30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, United States
継続期間: 2017 7 212017 7 26

出版物シリーズ

名前Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
2017-January

Other

Other30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
国/地域United States
CityHonolulu
Period17/7/2117/7/26

ASJC Scopus subject areas

  • 信号処理
  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Joint gap detection and inpainting of line drawings」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル