Scalable and easy-to-use sketch-based 3D model retrieval

• Project/Area Number: 26330133
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Multimedia database
• Research Institution: University of Yamanashi
• Principal Investigator: OHBUCHI Ryutarou 山梨大学, 総合研究部, 教授 (80313782)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Project Status: Completed (Fiscal Year 2016)
• Budget Amount: ¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000); Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2014: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
• Keywords: 3次元形状検索 / スケッチ検索 / 3次元形状特徴 / 多様体学習 / 深層学習 / マルチメディア検索 / 3次元形状モデル / 部分の例示による検索 / 画像検索 / スケッチによる３Dモデル検索 / 形状モデリング / 機械学習 / コンピュータビジョン

Outline of Final Research Achievements

Aiming for a convenient and scalable sketch-based 3 D model retrieval system, we worked on the following three sub-goals; (1) A sketch-based 3D shape retrieval algorithm having an interactive sketch drawing assistance feature driven by sketch based image retrieval technology, (2) A part-based 3D shape retrieval algorithm that employs randomized volume subdivision by using numerous subvolumes having random position, orientation and size, (3) A fast 3D shape comparison algorithm by using binarized feature vector that are generated directly or indirectly from 3D shapes and compared in Hamming space.

Research Products

• [Journal Article] Aggregating sparse binarized local features by summing for efficient 3D model retrieval (2016)
  • Author(s): Takahiko Furuya, Ryutarou Ohbuchi
  • Journal Title: Proc. of the Second IEEE Int’l Conf. on Multimedia Big Data (BigMM 2016) Volume: ISBN: 978-1-5090-2179-6 Pages: 314-321
  • DOI: 10.1109/bigmm.2016.32
  • Peer Reviewed
• [Journal Article] Accurate Aggregation of Local Features by using K-sparse Autoencoder for 3D Model Retrieval (2016)
  • Author(s): Takahiko Furuya, Ryutarou Ohbuchi
  • Journal Title: Proc. ACM International Conference on Multimedia Retrieval 2016 (ICMR2016) Volume: ISBN: 978-1-4503-4359-6 Pages: 293-297
  • DOI: 10.1145/2911996.2912054
  • Peer Reviewed
• [Journal Article] Deep Aggregation of Local 3D Geometric Features for 3D Model Retrieval (2016)
  • Author(s): Takahiko Furuya and Ryutarou Ohbuchi
  • Journal Title: Proc. British Machine Vision Conference (BMVC) 2016 Volume: BMVA2016 Pages: 1-12
  • Peer Reviewed / Open Access / Acknowledgement Compliant
• [Journal Article] 軽量な局所 2 値特徴を用いた 3 次元形状の比較 (2016)
  • Author(s): 松田隆広, 古屋貴彦, 大渕竜太郎
  • Journal Title: 情報処理学会論文誌 Volume: 57(11) Pages: 2456-2466
  • NAID: 170000131101
  • Peer Reviewed / Acknowledgement Compliant
• [Journal Article] リアルタイム作画支援を備えたスケッチによる3次元モデル検索システム (2016)
  • Author(s): 長田 茜, 古屋 貴彦, 大渕 竜太郎
  • Journal Title: Visual Computing / グラフィクスと CAD 合同シンポジウム 論文集 Volume: 2016 Pages: 1-8
  • Peer Reviewed
• [Journal Article] Range Scans based 3D Shape Retrieval (2015)
  • Author(s): Godil, A.; Dutagaci, H.; Bustos, B.; Choi, S.; Dong, S.; Furuya, T.; Li, H.; Link, N.; Moriyama, A.; Meruane, R.; Ohbuchi, R.; Paulus, D.; Schreck, T.; Seib, V.; Sipiran, I.; Yin, H.; Zhang, C.
  • Journal Title: Proc. Eurographics Workshop on 3D Object Retrieval Volume: Proceedings Pages: 153-160
  • DOI: 10.2312/3dor.20151069
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Non-rigid 3D Shape Retrieval (2015)
  • Author(s): Lian, Z.; Zhang, J.; Choi, S.; ElNaghy, H.; El-Sana, J.; Furuya, T.; Giachetti, A.; Guler, R. A.; Lai, L.; Li, C.; Li, H.; Limberger, F. A.; Martin, R.; Nakanishi, R. U.; Neto, A. P.; Nonato, L. G.; Ohbuchi, R.; Pevzner, K.; Pickup, D.; Rosin, P.; Sharf, A.; Sun, L.; Sun, X.; Tari, S.; Unal, G.; Wilson, R. C.
  • Journal Title: Proc. Eurographics Workshop on 3D Object Retrieval Volume: Proceedings Pages: 107-120
  • DOI: 10.2312/3dor.20151064
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Diffusion-on-Manifold Aggregation of Local Features for Shape-based 3D Model Retrieval (2015)
  • Author(s): Takahiko Furuya, Ryutarou Ohbuchi
  • Journal Title: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval Volume: Proceedings Pages: 171-178
  • DOI: 10.1145/2671188.2749380
  • Peer Reviewed / Acknowledgement Compliant
• [Journal Article] A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries (2015)
  • Author(s): B. Li, Y. Lu, C. Li, A. Godil, T. Schreck, M. Aono, M. Burtscher, Q. Chen, N. Chowdhury, B. Fang, H. Fu, T. Furuya, H. Li, J. Liu, H. Johan, R. Kosaka, H. Koyanagi, R. Ohbuchi, A. Tatsuma, Y. Wan, C. Zhang, C. Zou
  • Journal Title: Computer Vision and Image Understanding Volume: 131 Pages: 1-27
  • DOI: 10.1016/j.cviu.2014.10.006
  • Peer Reviewed
• [Journal Article] Similarity Metric Learning for Sketch-based 3D Object Retrieval (2014)
  • Author(s): Takahiko FURUYA and Ryutarou OHBUCHI
  • Journal Title: Multimedia Tools and Applications Volume: 72
  • DOI: 10.1007/s11042-014-2171-3
  • Peer Reviewed
• [Presentation] リアルタイム作画支援を備えたスケッチによる3次元モデル検索システム (2016)
  • Author(s): 長田 茜, 古屋 貴彦, 大渕 竜太郎
  • Organizer: Visual Computing / グラフィクスと CAD 合同シンポジウム 2016
  • Place of Presentation: 早稲田大学国際会議場（東京）
  • Year and Date: 2016-06-18
• [Presentation] Deep Convolutional Neural Networkを用いた物体の3軸回転に頑強な3次元形状比較に向けて (2016)
  • Author(s): 池谷 健，古屋 貴彦，大渕 竜太郎
  • Organizer: Visual Computing / グラフィクスと CAD 合同シンポジウム 2016
  • Place of Presentation: 早稲田大学国際会議場（東京）
  • Year and Date: 2016-06-18
• [Presentation] Hashing Cross-Modal Manifold for Scalable Sketch-based 3D Model Retrieval (2014)
  • Author(s): Takahiko FURUYA and Ryutarou OHBUCHI
  • Organizer: International Conference on 3D Vision (3DV) 2014, （査読有り）
  • Place of Presentation: Tokyo, Japan, DOI:10.1109/3DV.2014.72
  • Year and Date: 2014-12-08 – 2014-12-11
• [Presentation] Fusing Multiple Features for Shape-based 3D Model Retrieval (2014)
  • Author(s): Takahiko FURUYA and Ryutarou OHBUCHI
  • Organizer: British Machine Vision Conference (BMVC) 2014, （査読有り）
  • Place of Presentation: Nottingham, U.K
  • Year and Date: 2014-09-01 – 2014-09-05
• [Presentation] Lightweight binary voxel shape features for 3D data matching and retrieval (2014)
  • Author(s): Takahiro Matsuda, Takahiko Furuya, Ryutarou Ohbuchi
  • Organizer: First IEEE Int’l Conf. on Multimedia Big Data (BigMM) 2015, （査読有り）
  • Place of Presentation: Beijing, China
  • Year and Date: 2014-04-20 – 2015-04-22
• [Presentation] Large Scale Comprehensive 3D Shape Retrieval (2014)
  • Author(s): B. Li, Y. Lu, C. Li, A. Godil, T. Schreck, M. Aono, Q. Chen, N. K. Chowdhury, B. Fang, T. Furuya, H. Johan, R. Kosaka, H. Koyanagi, R. Ohbuchi, A. Tatsuma
  • Organizer: Eurographics Workshop on 3D Object Retrieval 2014 (3DOR 2014), （査読有り）
  • Place of Presentation: Strasbourg, France, DOI: 10.2312/3dor.20141059
  • Year and Date: 2014-04-06
• [Presentation] Extended Large Scale Sketch-Based 3D Shape Retrieval (2014)
  • Author(s): B. Li, Y. Lu, C. Li, A. Godil, T. Schreck, M. Aono, M. Burtscher, H. Fu, T. Furuya, H. Johan, J. Liu, R. Ohbuchi, A. Tatsuma, and C. Zou
  • Organizer: Eurographics Workshop on 3D Object Retrieval 2014 (3DOR 2014), （査読有り）
  • Place of Presentation: Strasbourg, France, DOI: 10.2312/3dor.20141058
  • Year and Date: 2014-04-06
• [Remarks] 大渕のWebページ
  • URL: http://www.kki.yamanashi.ac.jp/~ohbuchi/
• [Remarks] 大渕の論文リストページ
  • URL: http://www.kki.yamanashi.ac.jp/~ohbuchi/publication.html
• [Remarks] 大渕のGoogle Scholarページ
  • URL: https://scholar.google.co.jp/citations?user=-NOU6eYAAAAJ