Method and device for learning 3d model reconstruction

A learning device for 3D model reconstruction, the learning device comprising:

• a memory configured to store a learning image, a 3D model of an object within the learning image, and a 3D reconstruction model;
• and
• at least one processor connected to the memory,
• wherein the at least one processor is configured to:
• extract a point related to the object in the learning image from the learning image for the 3D reconstruction model;
• obtain a gradient map including surrounding context information in three dimensions of the point from the 3D model of the object;
• determine a weight of the point based on the learning image and the gradient map;
• and
• learn the 3D reconstruction model by using the weight such that the 3D model of the object is output from the 3D reconstruction model into which the learning image is entered.