• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Explore how to facilitate the human creative process from the perspective of Computer G raphics

Research Project

Project/Area Number 21F20075
Research Category

Grant-in-Aid for JSPS Fellows

Allocation TypeSingle-year Grants
Section外国
Review Section Basic Section 61020:Human interface and interaction-related
Research InstitutionThe 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)
  • 2022 Annual Research Report
  • 2021 Annual Research Report
  • Research Products

    (12 results)

All 2023 2022 2021 Other

All Journal Article (4 results) (of which Int'l Joint Research: 4 results,  Peer Reviewed: 4 results,  Open Access: 1 results) Presentation (2 results) (of which Int'l Joint Research: 2 results) Remarks (6 results)

  • [Journal Article] 360MVSNet: Deep Multi-view Stereo Network with 360° Images for Indoor Scene Reconstruction2023

    • Author(s)
      Chiu Ching-Ya、Wu Yu-Ting、Shen I-Chao、Chuang Yung-Yu
    • Journal Title

      WACV

      Volume: 0 Pages: 0-0

    • DOI

      10.1109/wacv56688.2023.00307

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] StyleFaceUV: a 3D Face UV Map Generator for View-Consistent Face Image Synthesis2023

    • Author(s)
      Wei-Chieh Chung, Jian-Kai Zhu, I-Chao Shen, Yu-Ting Wu, Yung-Yu Chuang
    • Journal Title

      BMVC

      Volume: 0 Pages: 0-0

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] ClipGen: A Deep Generative Model for Clipart Vectorization and Synthesis2022

    • Author(s)
      Shen I-Chao、Chen Bing-Yu
    • Journal Title

      IEEE Transactions on Visualization and Computer Graphics

      Volume: 28 Issue: 12 Pages: 4211-4224

    • DOI

      10.1109/tvcg.2021.3084944

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Data-driven Sketch Beautification with Neural Feature Representation2021

    • Author(s)
      Shen I-Chao
    • Journal Title

      IEEE Computer Graphics and Applications

      Volume: 1 Issue: 4 Pages: 1-1

    • DOI

      10.1109/mcg.2021.3115181

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] ODEN: Live Programming for Neural Network Architecture Editing2022

    • Author(s)
      Chunqi Zhao, I-Chao Shen, Tsukasa Fukusato, Jun Kato, Takeo Igarashi
    • Organizer
      26th International Conference on Intelligent User Interfaces (IUI 2022)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Per Garment Capture and Synthesis for Real-time Virtual Try-on2021

    • Author(s)
      Toby Chong, I-Chao Shen, Nobuyuki Umetani, Takeo Igarashi
    • Organizer
      User Interface Software and Technology (UIST) 2021
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Remarks] StyleFaceUV

    • URL

      https://jdily.github.io/proj_site/stylefaceuv_proj.html

    • Related Report
      2022 Annual Research Report
  • [Remarks] 360MVSNet

    • URL

      https://jdily.github.io/proj_site/360mvsnet_proj.html

    • Related Report
      2022 Annual Research Report
  • [Remarks] ClipGen

    • URL

      https://jdily.github.io/proj_site/clipgen_proj.html

    • Related Report
      2022 Annual Research Report
  • [Remarks] リアルタイムバーチャル試着のための衣服ごとのキャプチャと合成

    • URL

      https://sites.google.com/view/deepmannequin

    • Related Report
      2021 Annual Research Report
  • [Remarks] 神経特徴量表現を用いたデータ駆動型スケッチ美化手法

    • URL

      https://jdily.github.io/proj_site/ddsb_proj.html

    • Related Report
      2021 Annual Research Report
  • [Remarks] ODEN: ニューラルネットワークアーキテクチャ編集のためのライブプログラミング

    • URL

      https://haremi.xyz/projects/oden/oden.html

    • Related Report
      2021 Annual Research Report

URL: 

Published: 2021-05-27   Modified: 2024-03-26  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi