Higher-order function networks for learning composable three-dimensional (3D) object and operating method thereof

A method of representing a three-dimensional (3D) object, the method being performed by an augmented reality (AR) glasses worn by a user, and the method comprising:

• obtaining a two-dimensional (2D) image of an object using a camera;
• transmitting the 2D image to a server device;
• based on the 2D image being transmitted, receiving, from the server device, mapping function parameters that are obtained using a first neural network;
• setting a mapping function of a second neural network, based on the received mapping function parameters;
• and
• based on 3D samples, obtaining an 3D object corresponding to the 2D image, using the second neural network of which the mapping function is set.

A non-transitory computer-readable storage medium storing instructions configured to cause a processor to:

• obtain a two-dimensional (2D) image of an object using a camera;
• transmit the 2D image to a server device;
• based on the 2D image being transmitted, receive, from the server device, mapping function parameters that are obtained using a first neural network;
• set a mapping function of a second neural network, based on the received mapping function parameters;
• and
• based on three-dimensional (3D) samples, obtain an 3D object corresponding to the 2D image, using the second neural network of which the mapping function is set.