Photorealistic Augmented Reality Image Generation with Generative Adversarial Network Focusing on Structural Edge
-
- Iketani Shunya
- Graduate School of Science and Technology, Kwansei Gakuin University
-
- Imura Masataka
- School of Engineering, Kwansei Gakuin University
Bibliographic Information
- Other Title
-
- 3次元構造エッジを重視したGANによる写実的AR画像の生成
Description
<p>In order to represent virtual objects photorealistically in augmented reality (AR), the problem of optical consistency is important. There are several methods to achieve optical consistency using known real objects and special cameras, but they are difficult to use in AR applications. In this research, we propose an end-to-end method to convert an optically inconsistent AR image into an optically consistent AR image using a generative adversarial network (GAN). In addition, we propose a GAN that focuses on the structural edges of virtual objects in order to be able to handle different virtual object shapes. We confirmed that the GAN can generate photorealistic AR images consistent with the real world and that it is possible to generate images with versatility for virtual object shapes.</p>
Journal
-
- Transactions of the Institute of Systems, Control and Information Engineers
-
Transactions of the Institute of Systems, Control and Information Engineers 35 (6), 133-144, 2022-06-15
THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE)
- Tweet
Details 詳細情報について
-
- CRID
- 1390293424296397440
-
- ISSN
- 2185811X
- 13425668
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- Crossref
- OpenAIRE
-
- Abstract License Flag
- Disallowed