Representing 3D shapes based on implicit surface functions learned from RBF neural networks

Guoyu Lu, Li Ren, Abhishek Kolagunda, Xiaolong Wang, Ismail Baris Turkbey, Peter L. Choyke, Chandra Kambhamettu

Abstract: Highlights • We propose a 3D shape representation method based on neural network classifier. • The combination of radial base functions can implicitly represent complex shapes. • The use of neural network can represent the shape with 3 classes of points. • We conduct extensive experiments on medical and non-medical data. • Our method can accurately and memory-efficiently represent shapes. • We introduced a new prostate dataset. Abstract We propose to represent the shape of 3D objects using a neural network classifier. The 3D shape is learned from a neural network, where Radial Basis Function (RBF) is applied as the activation function for each perceptron. The implicit functions derived from the neural network is a combination of radial basis functions, which can represent complex shapes. The use of RBF provides a rotation, translation and scaling invariant feature to represent the shape. We conduct experiments on a new prostate dataset and public datasets. Our testing results show that our neural network-based method can accurately represent various shapes.