Deep learning for non-rigid 3D shape classification based on informative images

In order to enhance the discernment of features in view-based 3D shape recognition, we propose a joint convolutional neural network (CNN) learning model based on informative images. It learns deep features from intrinsic feature images and extrinsic 2D views, and generates a synthetic feature vector via weighted aggregation and refinement process, which has achieved remarkable improvement in non-rigid 3D shape classification. Our joint CNNs model contains three parts: the first part is the geometry-based feature generation unit. We provide a discriminative BoF (bag of features) image descriptor and construct CNN framework to learn the geometric features of the model. The second part is the view-based feature generation unit. We establish a parallel CNN to extract spatial features from optimized 2D views. The third part is a score generation and refinement unit, which automatically learns the weighted scores of geometric features and spatial features. Finally, the aggregated feature is refined in a CNN framework and serves as an informative shape descriptor for recognition task. The experimental results demonstrate that our deep features have the strong discerning ability. Thus, better performance and robustness can be obtained compared to state-of-the-art methods.