Fine-Grained 3D Shape Classification with Hierarchical Part-View Attentions

Fine-grained 3D shape classification is important and research challenging for shape understanding and analysis. However, due to the lack of fine-grained 3D shape benchmark, research on fine-grained 3D shape classification has rarely been explored. To address this issue, we first introduce a new dataset of fine-grained 3D shapes, which consists of three categories including airplane, car and chair. Each category consists of several subcategories at a fine-grained level. According to our experiments under this fine-grained dataset, we find that state-of-the-art methods are significantly limited by the small variance among subcategories in the same category. To resolve this problem, we further propose a novel fine-grained 3D shape classification method named FG3D-Net to capture the fine-grained local details of 3D shapes from multiple rendered views. Specifically, we first train a Region Proposal Network (RPN) to detect the generally semantic parts inside multiple views under the benchmark of generally semantic part detection. Then, we design a hierarchical part-view attention aggregation module to learn global shape representation by aggregating generally semantic part features, which preserves the local details of 3D shapes. The part-view attention module leverages a part-level attention and a view-level attention to increase the discriminative ability of features, where the part-level attention highlights the important parts in each view while the view-level attention highlights the discriminative views among all the views from the same object. In addition, we integrate the Recurrent Neural Network (RNN) to capture the spatial relationships among sequential views from different viewpoints. Our results under the fine-grained 3D shape dataset show that our method outperforms other state-of-the-art methods.