Deep Common Semantic Space Embedding for Sketch-Based 3D Model Retrieval
Sketch-based 3D model retrieval has become an important research topic in many applications, such as computer graphics and computer-aided design. Although sketches and 3D models have huge interdomain visual perception discrepancies, and sketches of the same object have remarkable intradomain visual...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-04-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/21/4/369 |
| _version_ | 1811304811870552064 |
|---|---|
| author | Jing Bai Mengjie Wang Dexin Kong |
| author_facet | Jing Bai Mengjie Wang Dexin Kong |
| author_sort | Jing Bai |
| collection | DOAJ |
| description | Sketch-based 3D model retrieval has become an important research topic in many applications, such as computer graphics and computer-aided design. Although sketches and 3D models have huge interdomain visual perception discrepancies, and sketches of the same object have remarkable intradomain visual perception diversity, the 3D models and sketches of the same class share common semantic content. Motivated by these findings, we propose a novel approach for sketch-based 3D model retrieval by constructing a deep common semantic space embedding using triplet network. First, a common data space is constructed by representing every 3D model as a group of views. Second, a common modality space is generated by translating views to sketches according to cross entropy evaluation. Third, a common semantic space embedding for two domains is learned based on a triplet network. Finally, based on the learned features of sketches and 3D models, four kinds of distance metrics between sketches and 3D models are designed, and sketch-based 3D model retrieval results are achieved. The experimental results using the Shape Retrieval Contest (SHREC) 2013 and SHREC 2014 datasets reveal the superiority of our proposed method over state-of-the-art methods. |
| first_indexed | 2024-04-13T08:14:00Z |
| format | Article |
| id | doaj.art-d3c842a21eb940579f92dac0226b7472 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-13T08:14:00Z |
| publishDate | 2019-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-d3c842a21eb940579f92dac0226b74722022-12-22T02:54:52ZengMDPI AGEntropy1099-43002019-04-0121436910.3390/e21040369e21040369Deep Common Semantic Space Embedding for Sketch-Based 3D Model RetrievalJing Bai0Mengjie Wang1Dexin Kong2School of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSketch-based 3D model retrieval has become an important research topic in many applications, such as computer graphics and computer-aided design. Although sketches and 3D models have huge interdomain visual perception discrepancies, and sketches of the same object have remarkable intradomain visual perception diversity, the 3D models and sketches of the same class share common semantic content. Motivated by these findings, we propose a novel approach for sketch-based 3D model retrieval by constructing a deep common semantic space embedding using triplet network. First, a common data space is constructed by representing every 3D model as a group of views. Second, a common modality space is generated by translating views to sketches according to cross entropy evaluation. Third, a common semantic space embedding for two domains is learned based on a triplet network. Finally, based on the learned features of sketches and 3D models, four kinds of distance metrics between sketches and 3D models are designed, and sketch-based 3D model retrieval results are achieved. The experimental results using the Shape Retrieval Contest (SHREC) 2013 and SHREC 2014 datasets reveal the superiority of our proposed method over state-of-the-art methods.https://www.mdpi.com/1099-4300/21/4/369sketch-based retrieval3D model retrievaldeep common semantic space embeddingmetric learningcross-entropy |
| spellingShingle | Jing Bai Mengjie Wang Dexin Kong Deep Common Semantic Space Embedding for Sketch-Based 3D Model Retrieval Entropy sketch-based retrieval 3D model retrieval deep common semantic space embedding metric learning cross-entropy |
| title | Deep Common Semantic Space Embedding for Sketch-Based 3D Model Retrieval |
| title_full | Deep Common Semantic Space Embedding for Sketch-Based 3D Model Retrieval |
| title_fullStr | Deep Common Semantic Space Embedding for Sketch-Based 3D Model Retrieval |
| title_full_unstemmed | Deep Common Semantic Space Embedding for Sketch-Based 3D Model Retrieval |
| title_short | Deep Common Semantic Space Embedding for Sketch-Based 3D Model Retrieval |
| title_sort | deep common semantic space embedding for sketch based 3d model retrieval |
| topic | sketch-based retrieval 3D model retrieval deep common semantic space embedding metric learning cross-entropy |
| url | https://www.mdpi.com/1099-4300/21/4/369 |
| work_keys_str_mv | AT jingbai deepcommonsemanticspaceembeddingforsketchbased3dmodelretrieval AT mengjiewang deepcommonsemanticspaceembeddingforsketchbased3dmodelretrieval AT dexinkong deepcommonsemanticspaceembeddingforsketchbased3dmodelretrieval |