-
公开(公告)号:US20240394964A1
公开(公告)日:2024-11-28
申请号:US18669048
申请日:2024-05-20
Inventor: Seung-Hwan BAEK , Seokjun CHOI , Seungwoo YOON , Seungyong LEE , Jinwoo PARK , Nahyup KANG , Jiyeon KIM
Abstract: A method of determining an illumination pattern includes constructing a dataset by estimating a first surface normal vector of a three-dimensional (3D) object from a first image obtained by capturing the 3D object of which surface normal information is known, the dataset including basis images of the 3D object; generating simulation images in which virtual illumination patterns, obtained based on a combination of the basis images, are applied to the 3D object; estimating a second surface normal vector of the 3D object, by reconstructing a surface normal using a photometric stereo technique based on the virtual illumination patterns and simulation images corresponding to the virtual illumination patterns; and training a neural network to determine an illumination pattern based on a difference between the first surface normal vector and the second surface normal vector.
-
公开(公告)号:US20250131652A1
公开(公告)日:2025-04-24
申请号:US18908371
申请日:2024-10-07
Inventor: Seungyong LEE , Wonjong JANG , Hyomin KIM , Yucheol JUNG
IPC: G06T17/20 , G06T3/4007 , G06T3/4046 , G06T7/50 , G06T15/02
Abstract: A stylized 3D mesh generation device may comprise: a memory for storing at least one or more instructions; a processor for executing the at least one or more instructions; a first neural network for generating a per-pixel feature vector based on a 2D input image and a target style; and a second neural network for generating a surface normal map corresponding to a 3D mesh of the 2D input image based on the per-pixel feature vector, wherein the processor generates a stylized 3D mesh of the 2D input image based on the surface normal map, and the second neural network generates and outputs the surface normal map applied with the target style based on the per-pixel feature vector.
-