Explore how to facilitate the human creative process from the perspective of Computer G raphics
| Project/Area Number |
21F20075
|
|---|
| Research Category |
Grant-in-Aid for JSPS Fellows
|
| Allocation Type | Single-year Grants |
|---|
| Section | 外国 |
|---|
| Review Section |
Basic Section 61020:Human interface and interaction-related
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
五十嵐 健夫 東京大学, 大学院情報理工学系研究科, 教授 (80345123)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
SHEN I-CHAO 東京大学, 情報理工学(系)研究科, 外国人特別研究員
|
|---|
| Project Period (FY) |
2021-04-28 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥2,300,000 (Direct Cost: ¥2,300,000)
Fiscal Year 2022: ¥1,100,000 (Direct Cost: ¥1,100,000)
Fiscal Year 2021: ¥1,200,000 (Direct Cost: ¥1,200,000)
|
|---|
| Keywords | コンピューターグラフィックス / 機械学習 / コンピュータグラフィックス / 設計支援アルゴリズム |
|---|
| Outline of Research at the Start |
Our research aims to solve the problem of inverse polygonal modeling, which generates a semantically-meaningful editing history given several image-based observations. We will analyze the types of editing operations used in the polygonal modeling process, and focus on designing a scoring model to infer the most likely topological operations that lead to the target image-based observations. At the same time, we also need to design a data generation process that generates useful training data for our scoring model.
|
| Outline of Annual Research Achievements |
In the past year, I have worked on seven projects and had four papers accepted.
The main theme of these projects is (1) to increase the ability of the generative model by providing user inputs and (2) to assist users in creating ML algorithms. These projects are relevant to edit nerf model and capturing nerf model, image-based shape part manipulation, indoor scene reconstruction from 360 images, and layout generation for graphic design.
In more detail, I introduce the first framework that enables users to remove unwanted objects or retouch undesired regions in a 3D scene represented by a pre-trained NeRF without any category-specific data and training. On the other hand, I proposed a novel containment-aware loss function for layout generation.
|
| Research Progress Status |
令和4年度が最終年度であるため、記入しない。
|
| Strategy for Future Research Activity |
令和4年度が最終年度であるため、記入しない。
|
Report
(2 results)
Research Products
(12 results)
