Skip to main content

3D Model Retrieval Algorithm Based on Attention and Multi-view Fusion.

Shi, Z., Quan, Z., Shi, J., Guo, Z., Zhang, M. and Xiao, Z., 2022. 3D Model Retrieval Algorithm Based on Attention and Multi-view Fusion. In: 5th International conference on Computer Graphics, Image and Visualization (CCGIV2022), 2022-10-21 - 2022-10-23, Guilin, China. (Unpublished)

Full text available as:

3D Model Retrieval Algorithm Based on Attention and Multi-view Fusion.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.


Official URL:


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.

Item Type:Conference or Workshop Item (Paper)
Group:Faculty of Media & Communication
ID Code:38038
Deposited By: Symplectic RT2
Deposited On:22 Dec 2023 11:52
Last Modified:22 Dec 2023 11:52


Downloads per month over past year

More statistics for this item...
Repository Staff Only -