360-Degree Image Completion by Two-Stage Conditional Gans

Naofumi Akimoto, Seito Kasai, Masaki Hayashi, Yoshimitsu Aoki

研究成果: Conference contribution

5 被引用数 (Scopus)

抄録

The latest generative adversarial networks (GANs) can generate realistic high resolution images. However, to the best of our knowledge, there are no GANs for generating 360-degree images. Therefore, this paper proposes the novel problem setting that by using a known area from the 360-degree image as an input, the remainder of the image can be completed with the GANs. To do so, we propose the approach of two-stage generation using network architecture with series-parallel dilated convolution layers. Moreover, we present how to rearrange images for data augmentation, simplify the problem, and make inputs for training the 2nd stage generator. Our experiments show that these methods generate the distortion seen in 360-degree images in the outlines of buildings and roads, and their boundaries are clearer than those of baseline methods. Furthermore, we discuss and clarify the difficulty of our proposed problem. Our work is the first step towards GANs predicting an unseen area within a 360-degree space.

本文言語English
ホスト出版物のタイトル2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
出版社IEEE Computer Society
ページ4704-4708
ページ数5
ISBN(電子版)9781538662496
DOI
出版ステータスPublished - 2019 9月
イベント26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China
継続期間: 2019 9月 222019 9月 25

出版物シリーズ

名前Proceedings - International Conference on Image Processing, ICIP
2019-September
ISSN(印刷版)1522-4880

Conference

Conference26th IEEE International Conference on Image Processing, ICIP 2019
国/地域Taiwan, Province of China
CityTaipei
Period19/9/2219/9/25

ASJC Scopus subject areas

  • ソフトウェア
  • コンピュータ ビジョンおよびパターン認識
  • 信号処理

フィンガープリント

「360-Degree Image Completion by Two-Stage Conditional Gans」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