.png){kind=icon}
.png){kind=icon}
Return
Dynamic View Aggregation for Multi-View 3D Shape Recognition
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2024.3387656.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In the field of 3D shape recognition, the view-based approach has achieved state-of-the-art performance. A major challenge that needs to be addressed by the view-based approach is how to effectively aggregate multi-view features to obtain a better 3D shape representation. Existing methods which rely on networks with static parameters for feature aggregation adversely coerce the network to learn a general feature aggregation strategy for all inputs, ignoring the diversity of input 3D shapes in real-world scenarios. In this work, we propose a novel Dynamic View Aggregation Network called DVA-Net to address this challenge. DVA-Net can dynamically adjust the network parameter depending on the input 3D shapes to flexibly fuse multi-view information. The shape-specific parameter adaptation is achieved by our designed Dynamic Relation-aware Aggregation module, dubbed DRA module. It is responsible for learning relations among views and adaptively integrating multi-view features. Comprehensive experiments on benchmark datasets demonstrate that our proposed method achieves state-of-the-art performance for 3D shape classification and retrieval.
Keywords:
Shape
Three-dimensional displays
Feature extraction
Aggregates
Task analysis
Image recognition
Fuses
3D shape recognition
view-based method
dynamic view aggregation
Journal
IF:
9.7
Papers:
4.5K
Citations:
2.4W