FVCNN: Fusion View Convolutional Neural Networks for Non-rigid 3D Shape Classification and Retrieval

Most 3D shape classification and retrieval algorithms were based on rigid 3D shapes, deploying these algorithms directly to non-rigid 3D shapes may lead to poor performance due to complexity and changeability of non-rigid 3D shapes. To address this challenge, we propose a fusion view convolutional neural networks (FVCNN) framework to extract the deep fusion features for non-rigid 3D shape classification and retrieval. We first propose a projection module to transform the non-rigid 3D shape into a 2D view plane. We then propose a feature coding module to extract the new scale invariance heat kernel signature (NS) feature and structural relationship (SR) feature of the 3D shape, which are used as the pixel values on the projection points of the corresponding vertices to generate two views, respectively. Finally, we propose a fusion module based on CNNs to extract the view-based features, which are fused to extract the deep fusion features as the 3D shape descriptors. The experiments on standard dataset SHREC show that our method outperforms the state-of-the-art methods on non-rigid 3D shape classification and retrieval.