| Project/Area Number |
18K18077
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 61010:Perceptual information processing-related
|
|---|
| Research Institution | University of Tsukuba |
|---|
Principal Investigator |
Satoshi Iizuka 筑波大学, システム情報系, 助教 (30755153)
|
|---|
| Project Period (FY) |
2018-04-01 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2020: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2019: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2018: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
|
|---|
| Keywords | 経年変化 / 深層学習 / 画像処理 / 経年劣化 / 画像編集 |
|---|
| Outline of Final Research Achievements |
In order to reproduce the decay of objects in natural images, we worked on developing an image weathering generation method using deep learning. To this end, we constructed a dataset of weathering texture images and trained a deep generative neural network on the texture dataset. This weathering texture generator network is able to generate arbitrary weathering textures such as rust and moss. The users can easily make various weathering images using the proposed method without special knowledge and skills in image processing.
|
| Academic Significance and Societal Importance of the Research Achievements |
画像の経年変化の再現技術は，実世界の景観や物体がどのように変化していくかを視覚的かつ直感的に伝えることができるため，都市計画における景観予測やエンターテインメント分野におけるコンテンツ制作など、幅広い応用が期待できる．学術的にも，深層学習を活用して画像の経年劣化を再現する技術はこれまでになく，本研究成果はこのタスクにおける新たなアプローチとして当該研究分野の発展に貢献できると考えられる。
|
