3D Model Retrieval Algorithm Based on Attention and Multi-view Fusion
Open Access
- 21 October 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 474-480
Abstract
With the rapid development of computer vision, 3D data is increasing rapidly. How to retrieve similar model from a large number of models has become a hot research topic. However, in order to meet people's demand, the retrieval accuracy need to be further improved. In terms of multi-view 3D model retrieval, how to effectively learn the information between views is the key to improving performance. In this paper, we propose a novel 3D model retrieval algorithm based on attention and multi-view fusion. Specifically, we mainly constructed two modules. First, dynamic attentive graph learning module is used to learn the intrinsic relationship between view blocks; Then we propose the Attention-NetVlad algorithm, which combines the channel attention algorithm and the NetVlad algorithm. It learns the information between feature channels to enhance the feature expression ability firstly, then uses the NetVlad algorithm to fuse multiple view features into a global feature according to the clustering information. Finally the global feature is used as the only feature of the model to retrieve according to Euclidean distance. In comparison with other state-of-the-art methods by utilizing ModelNet10 and ModelNet40 the proposed method has demonstrated significant improvement for retrieval mAP. Our experiments also demonstrate the effectiveness of the modules in the algorithm.Keywords
Funding Information
- Natural Science Foundation of Hebei Province (F2019202054)
This publication has 24 references indexed in Scilit:
- NormalNet: A voxel-based CNN for 3D object classification and retrievalNeurocomputing, 2019
- SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With AttentionIEEE Transactions on Image Processing, 2018
- Multi-scale CNNs for 3D model retrievalMultimedia Tools and Applications, 2018
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
- Deep Residual Learning for Image Recognition2016
- NetVLAD: CNN Architecture for Weakly Supervised Place Recognition2016
- Deep Aggregation of Local 3D Geometric Features for 3D Model Retrieval2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- 3D ShapeNets: A deep representation for volumetric shapes2015
- On Visual Similarity Based 3D Model RetrievalComputer Graphics Forum, 2003