| 作成者 |
|
|
|
| 本文言語 |
|
| 出版者 |
|
|
|
| 発行日 |
|
| 収録物名 |
|
| 巻 |
|
| 開始ページ |
|
| 終了ページ |
|
| 出版タイプ |
|
| アクセス権 |
|
| JaLC DOI |
|
| 概要 |
In this study, based on a learning data, we construct a deep learning model that generates realistic images and animations of plants from simple point inputs that specify the contents of images. In co...nventional image generation by deep learning, a rough input may be difficult because an input image for generation and an output image need to correspond one-to-one for each pixel. In addition, a large amount of input data is required to generate an animation. On the other hand, in a method of continuously changing an image by extracting and manipulating attributes of the image, it is difficult to obtain a highquality animation in which details are clearly expressed in the generation of a plant image. In this study, we construct a two-stage deep learning model using point labels as input. As a result, high-quality images and animations that plants smoothly change can be generated from a small amount of learning data. Quantitative evaluation of images and animations generated by this study showed that high-quality images were obtained that were clearer than existing methods and less biased in appearance attributes such as leaf arrangement and the size of the plant.続きを見る
|
Mendeley出力
