Research on Fine-grained 3D Shape Similarity Search and Automatic Captioning using Deep Learning
| Project/Area Number |
17H01746
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Multimedia database
|
|---|
| Research Institution | Toyohashi University of Technology |
|---|
Principal Investigator |
Aono Masaki 豊橋技術科学大学, 工学(系)研究科(研究院), 教授 (00372540)
|
|---|
| Project Period (FY) |
2017-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥13,650,000 (Direct Cost: ¥10,500,000、Indirect Cost: ¥3,150,000)
Fiscal Year 2020: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2019: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2018: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2017: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
|
|---|
| Keywords | 三次元形状類似検索 / 部分形状表現 / 三次元部分形状検索 / 3Dシーン / 3Dアセンブリ / 自動注釈付与 / 部分形状抽出 / 部分形状検索 / 3D検索 / アセンブリ形状モデル / 連結表現 / 注釈付与 / 物体検出 / 深層学習 / 3D形状 / マルチモーダル / 部分検索 / 自動注釈 / 静止物体認識 / 物体位置推定 / 移動物体検出 / 3D形状類似検索 / ベンチマーク / 3D / 検索 / 分類 / ３Ｄ形状類似検索 / ３Ｄシーン / 形状特徴量 |
|---|
| Outline of Final Research Achievements |
In this research, we have developed a fine-grained 3D shape-like search method based on deep learning, proposed new partial shape representations and a method for automatic annotation for objects in 3D scene. The target data is consists of a large amount of 3D objects typically seen in 3D scenes and 3D assembly databases.
First, we have developed a TVS (Tri-projection Voxel Splatting) method that can recognize 3D scenes with high precision. Second, we have developed a TBPSR (Topology Based Partial Shape Retrieval) method based on topological structure. Finally, by adding POS (Part-Of-Speech) information to the annotation during training stage, we have developed a novel automatic annotation method for highly accurate 3D scene images.
|
| Academic Significance and Societal Importance of the Research Achievements |
小規模～中規模の3Dデータ(データ数1万以下）のものでは、高精度な三次元形状類似検索が知られていたが、本研究を通して10万～100万程度のビッグデータかつ複雑な3Dデータに対して、細粒度な検索が可能な部分形状を定義できた。このことで、機械部品、輸送用機械に代表される製造業や建築産業に対して、大規模な3Dデータから、小領域空間にある部分形状だけ与えて、それを含む複雑な3Dシーンや3Dアセンブリが高精度に検索できるようになった。今回開発したスケーラブルな部分検索手法は我々が知る限り、実用化されていない。また、自動注釈付与技術は、膨大な3Dデータを管理するシステムに付加価値を与えてくれる意義を持つ。
|
Report
(5 results)
Research Products
(91 results)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] Large-Scale 3D Shape Retrieval from ShapeNet Core552017
Author(s)
Manolis Savva, Asako Kanezaki, Takahiko Furuya, Ryutarou Ohbuchi, Masaki Aono, Atsushi Tatsuma, S. Thermos, A. Axenopoulos, G. Th. Papadopoulos, P. Daras, Xiao Deng, Zhouhui Lian, Bo Li, st al.
Organizer
Eurographics Workshop on 3D Object Retrieval
Related Report
Int'l Joint Research
-
-
-
-
-
-
-
-
-
-
-
-
