Dynamic View Aggregation for Multi-View 3D Shape Recognition

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.