Abstract: A method for determining two-dimensional (2D) patches corresponding to a three-dimensional (3D) object using machine learning models for enabling an improved texture mapping process on the 3D object. The method includes (i) receiving mesh of the 3D object, (ii) training first machine learning model by providing correlation between historic vertices with (a) historic faces, and (b) historic vertex normals of historic meshes based on an objective function of patch extraction, (iii) determining, using the first machine learning model, 2D patches by partitioning the mesh until distortion of the mesh reaches threshold distortion, (iv) training second machine learning model using (i) shape-related features of historic 2D patches associated with historic meshes and (ii) an objective function of surface parameterization of the historic 2D patches associated with the historic meshes, and (v) automatically parameterizing each vertex in the 2D patches to 2D points on 2D plane to enable the texture mapping process.

Abstract: A system and method of reconstructing a three-dimensional (3D) model of a garment using an image are provided. The method includes (i) receiving a two-dimensional (2D) image from a user device associated with a user, (ii) representing the garment into a point cloud of the garment by extracting the garment from the 2D image, and (iii) reconstructing a three-dimensional (3D) image of the 2D image by generating a dense mesh of the garment by (a) splitting the set of 3D points into a mesh based on an image grid structure to identify the missing regions in the point cloud, (b) generating an additional mesh for the missing regions by sampling the set of 3D points on the point cloud using a Poisson surface reconstruction method, and (c) generating a dense mesh by combining the mesh with the additional mesh to fill the missing regions in the point cloud of the garment.