3D model retrieval based on interactive attention CNN and multiple features

被引:0
作者
Gao, Xue-Yao [1 ]
Jia, Wen-Hui [1 ]
Zhang, Chun-Xiang [1 ]
机构
[1] Harbin Univ Sci & Technol, Sch Comp Sci & Technol, Harbin, Peoples R China
关键词
3D model; Freehand sketch; 3D model retrieval; Interactive attention; 2D views; Euclidean distance; Shape distribution feature; SHAPE RETRIEVAL; SKETCH; NETWORK; CLASSIFICATION;
D O I
10.7717/peerj-cs.1227
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
3D (three-dimensional) models are widely applied in our daily life, such as mechanical manufacture, games, biochemistry, art, virtual reality, and etc. With the exponential growth of 3D models on web and in model library, there is an increasing need to retrieve the desired model accurately according to freehand sketch. Researchers are focusing on applying machine learning technology to 3D model retrieval. In this article, we combine semantic feature, shape distribution features and gist feature to retrieve 3D model based on interactive attention convolutional neural networks (CNN). The purpose is to improve the accuracy of 3D model retrieval. Firstly, 2D (two-dimensional) views are extracted from 3D model at six different angles and converted into line drawings. Secondly, interactive attention module is embedded into CNN to extract semantic features, which adds data interaction between two CNN layers. Interactive attention CNN extracts effective features from 2D views. Gist algorithm and 2D shape distribution (SD) algorithm are used to extract global features. Thirdly, Euclidean distance is adopted to calculate the similarity of semantic feature, the similarity of gist feature and the similarity of shape distribution feature between sketch and 2D view. Then, the weighted sum of three similarities is used to compute the similarity between sketch and 2D view for retrieving 3D model. It solves the problem that low accuracy of 3D model retrieval is caused by the poor extraction of semantic features. Nearest neighbor (NN), first tier (FT), second tier (ST), F-measure (E(F)), and discounted cumulated gain (DCG) are used to evaluate the performance of 3D model retrieval. Experiments are conducted on ModelNet40 and results show that the proposed method is better than others. The proposed method is feasible in 3D model retrieval.
引用
收藏
页码:1 / 19
页数:19
相关论文
共 32 条
[1]  
[白静 Bai Jing], 2019, [计算机辅助设计与图形学学报, Journal of Computer-Aided Design & Computer Graphics], V31, P2056
[2]   Learning High-Level Feature by Deep Belief Networks for 3-D Model Retrieval and Recognition [J].
Bu, Shuhui ;
Liu, Zhenbao ;
Han, Junwei ;
Wu, Jun ;
Ji, Rongrong .
IEEE TRANSACTIONS ON MULTIMEDIA, 2014, 16 (08) :2154-2167
[3]   Cross-domain retrieving sketch and shape using cycle CNNs [J].
Chen, Mingjia ;
Wang, Changbo ;
Liu, Ligang .
COMPUTERS & GRAPHICS-UK, 2020, 89 :50-58
[4]   Novel Sketch-Based 3D Model Retrieval via Cross-domain Feature Clustering and Matching [J].
Gao, Kai ;
Zhang, Jian ;
Li, Chen ;
Wang, Changbo ;
He, Gaoqi ;
Qin, Hong .
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2020, PT I, 2020, 12396 :299-311
[5]   Multi-Level View Associative Convolution Network for View-Based 3D Model Retrieval [J].
Gao, Zan ;
Zhang, Yan ;
Zhang, Hua ;
Guan, Weili ;
Feng, Dong ;
Chen, Shengyong .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (04) :2264-2278
[6]   OpenSketch: A Richly-Annotated Dataset of Product Design Sketches [J].
Gryaditskaya, Yulia ;
Sypesteyn, Mark ;
Hoftijzer, Jan Willem ;
Pont, Sylvia ;
Durand, Fredo ;
Bousseau, Adrien .
ACM TRANSACTIONS ON GRAPHICS, 2019, 38 (06)
[7]   SAC: Semantic Attention Composition for Text-Conditioned Image Retrieval [J].
Jandial, Surgan ;
Badjatiya, Pinkesh ;
Chawla, Pranit ;
Chopra, Ayush ;
Sarkar, Mausoom ;
Krishnamurthy, Balaji .
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022), 2022, :597-606
[8]   Cross-Domain Correspondence for Sketch-Based 3D Model Retrieval Using Convolutional Neural Network and Manifold Ranking [J].
Jiao, Shichao ;
Han, Xie ;
Xiong, Fengguang ;
Sun, Fusheng ;
Zhao, Rong ;
Kuang, Liqun .
IEEE ACCESS, 2020, 8 (08) :121584-121595
[9]  
Jing Zhang, 2017, International Journal of Innovative Computing, Information & Control, V13, P411
[10]  
Kim S, 2020, Img Proc Comp Vis Re, V12363, P175, DOI 10.1007/978-3-030-58523-5_11