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

Retrieval and detection of 3D shapes based on details of their parts

Research Project

Project/Area Number 18K11313
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 60080:Database-related
Research InstitutionUniversity of Yamanashi

Principal Investigator

OHBUCHI Ryutarou  山梨大学, 大学院総合研究部, 教授 (80313782)

Co-Investigator(Kenkyū-buntansha) 古屋 貴彦  山梨大学, 大学院総合研究部, 助教 (00770835)
Project Period (FY) 2018-04-01 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2020: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywordsマルチメディア検索 / 3次元点群データ解析 / 3次元形状類似比較 / ディープラーニング / 教師無し学習 / deep neural network / 3次元部分形状検索 / 3次元形状解析 / 3次元形状検索 / 3D形状比較 / 深層学習 / 3次元形状領域分割 / 部分3D形状比較 / 3D形状識別 / 3D形状領域分割 / 深層ニューラルネットワーク / 部分3次元形状比較 / 3次元形状のラベル付け / スケッチ検索 / データ拡張 / 3D shape retrieval / 3D shape recognition / multimedia retrieval / machine learning / computer vision
Outline of Final Research Achievements

This study tried to establish easy to use, efficient, and accurate methods for detailed 3D shape retrieval. We focused on following two areas; (1) semantic segmentation of a 3D shape into meaningful parts, data-driven association of partial shape and whole shape, unsupervised learning of 3D shape feature extractor, (2) query presentation and query navigation methods for detailed 3D shape retrieval using hand-drawn sketches, text, and other medium as input. We applied various supervised and unsupervised learning methods using deep neural networks for such issues as 3D shape feature extraction, association of heterogeneous features (e.g., sketches and 3D point sets), part-whole association, and shape similarity comparison.

Academic Significance and Societal Importance of the Research Achievements

2D画像やテキストに対する識別,検索などの処理の研究は深層ニューラルネットワーク(DNN)などの機械学習技術の追い風を受けて急速に進んでいる.一方,機械設計,映像コンテンツ制作,考古学,創薬など幅広い分野において3D形状の解析,比較,検索の技術が求められているがその技術は確立されていない.本研究では目標を「部分形状を検索要求とし,大量の3D(全体)形状の中から,検索要求と類似する形状を部分として持つ3D(全体)形状を,必要に応じてその詳細形状を指定しつつ高精度かつ高速に検索する」3D形状部分詳細形状検索技術に定め,その実現に必要な複数の要素技術について検討を行った.

Report

(4 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Research-status Report
  • 2018 Research-status Report
  • Research Products

    (13 results)

All 2020 2019 2018 Other

All Journal Article (10 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 9 results,  Open Access: 2 results) Remarks (3 results)

  • [Journal Article] Transcoding across 3D shape representations for unsupervised learning of 3D shape feature2020

    • Author(s)
      Takahiko Furuya, Ryutarou Ohbuchi
    • Journal Title

      Pattern Recognition Letters

      Volume: 138 Pages: 146-154

    • DOI

      10.1016/j.patrec.2020.07.012

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Convolution on Rotation-invariant and Multi-scale Feature Graph for 3D Point Set Segmentation2020

    • Author(s)
      Takahiko Furuya, Xu Hang, Ryutarou Ohbuchi, Jinliang Yao
    • Journal Title

      IEEE Access

      Volume: 8 Pages: 140250-140260

    • DOI

      10.1109/access.2020.3012613

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Cascaded Multi-Channel Feature Fusion for Object Detection2020

    • Author(s)
      He Lifei、Ohbuchi Ryutarou、Jiang Ming、Furuya Takahiko、Zhang Min
    • Journal Title

      Proc. ICCCV'20: 2020 the 3rd International Conference on Control and Computer Vision

      Volume: 0 Pages: 11-16

    • DOI

      10.1145/3425577.3425580

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Scale Adaptive Feature Pyramid Networks for 2D Object Detection2020

    • Author(s)
      He Lifei、Jiang Ming、Ohbuchi Ryutarou、Furuya Takahiko、Zhang Min、Li Pengfei
    • Journal Title

      Scientific Programming

      Volume: 2020 Pages: 1-8

    • DOI

      10.1155/2020/8839979

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Annotating 3D Models and Their Parts via Deep Feature Embedding2019

    • Author(s)
      Omata Kouki、Furuya Takahiko、Ohbuchi Ryutarou
    • Journal Title

      Proc. 2019 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)

      Volume: - Pages: 489-494

    • DOI

      10.1109/icmew.2019.00090

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] 敵対的生成ネットワークを用いた3次元点群形状特徴量の教師なし学習2019

    • Author(s)
      上西 和樹, 古屋 貴彦, 大渕 竜太郎
    • Journal Title

      情報処理学会論文誌

      Volume: 60 Pages: 1315-1324

    • NAID

      170000150489

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] Feature set aggregator: unsupervised representation learning of sets for their comparison2019

    • Author(s)
      Furuya Takahiko、Ohbuchi Ryutarou
    • Journal Title

      Multimedia Tools and Applications

      Volume: 78 Issue: 24 Pages: 35157-35178

    • DOI

      10.1007/s11042-019-08078-y

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Query by Partially-Drawn Sketches for 3D Shape Retrieval2019

    • Author(s)
      S. Kuwabara, R. Ohbuchi and T. Furuya
    • Journal Title

      Proc. 2019 International Conference on Cyberworlds (CW),

      Volume: - Pages: 69-76

    • DOI

      10.1109/cw.2019.00020

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] Data augmentation via photo-to-sketch translation for sketch-based image retrieval2019

    • Author(s)
      Furuya Takahiko、Ohbuchi Ryutarou
    • Journal Title

      Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018)

      Volume: 1106925 Pages: 69-69

    • DOI

      10.1117/12.2524230

    • Related Report
      2018 Research-status Report
    • Peer Reviewed
  • [Journal Article] 敵対的生成ネットワークを用いた,3次元点群形状特徴量の教師なし学習2018

    • Author(s)
      上西 和樹, 古屋 貴彦, 大渕 竜太郎
    • Journal Title

      研究報告コンピュータグラフィックスとビジュアル情報学(CG)

      Volume: 2018-CG-170 Pages: 1-7

    • NAID

      170000150489

    • Related Report
      2018 Research-status Report
  • [Remarks] Ohbuchi & Furuya Laboratory

    • URL

      http://www.kki.yamanashi.ac.jp/~ohbuchi/

    • Related Report
      2019 Research-status Report
  • [Remarks] 情報処理学会 論文賞 (2019年度)

    • URL

      https://www.ipsj.or.jp/award/ronbun-index.html

    • Related Report
      2019 Research-status Report
  • [Remarks] 2019年度論文賞受賞者の紹介

    • URL

      https://www.ipsj.or.jp/award/2019_03.html

    • Related Report
      2019 Research-status Report

URL: 

Published: 2018-04-23   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi