HRGE-Net: Hierarchical Relational Graph Embedding Network for Multi-view 3D Shape Recognition
This work addresses a key challenge in view-based 3D shape recognition for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of aggregating multi-view features for 3D shape recognition by proposing HRGE-Net, a hierarchical relational graph embedding network that models view relations, achieving state-of-the-art performance in classification and retrieval on benchmark datasets.
View-based approach that recognizes 3D shape through its projected 2D images achieved state-of-the-art performance for 3D shape recognition. One essential challenge for view-based approach is how to aggregate the multi-view features extracted from 2D images to be a global 3D shape descriptor. In this work, we propose a novel feature aggregation network by fully investigating the relations among views. We construct a relational graph with multi-view images as nodes, and design relational graph embedding by modeling pairwise and neighboring relations among views. By gradually coarsening the graph, we build a hierarchical relational graph embedding network (HRGE-Net) to aggregate the multi-view features to be a global shape descriptor. Extensive experiments show that HRGE-Net achieves stateof-the-art performance for 3D shape classification and retrieval on benchmark datasets.