公开(公告)号：US20250124678A1

公开(公告)日：2025-04-17

申请号：US18441528

申请日：2024-02-14

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Junseok KANG ,  SangChul AHN

IPC: G06T19/20 ,  G06T15/04 ,  G06T17/20

Abstract: According to a method and device for generating a head avatar using a shot video, a head mesh of neutral look and a head texture map of neutral look are generated based on a base mesh of a base model and at least one shooting image representing a face of neutral look among a plurality of shooting images generated from a camera shot video, and a head mesh reflecting a certain facial expression and a head texture reflecting the certain facial expression are generated based on at least one shooting image representing a face of a certain facial expression among the plurality of shooting images, the head mesh of neutral look, and the head texture map of neutral look.

公开(公告)号：US20220188557A1

公开(公告)日：2022-06-16

申请号：US17206849

申请日：2021-03-19

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Sang Chul AHN ,  Junseok KANG

IPC: G06K9/00 ,  G06K9/62 ,  G06K9/32

Abstract: The present disclosure relates to an object detection and classification system with higher accuracy and resolution in a less computer memory environment. The system comprises an input value generation unit to receive an input image and generate an input value including feature information; a memory value generation unit to receive a reference image and generate a memory value including feature information; a memory management unit to select information having high importance from the memory values and store in a computer memory; an aggregated value generation unit to compute similarity between the input value and the memory value, calculate a weighted sum to generate an integrated value, and aggregate the integrated value and the input value; and an object detection unit to detect or classify the object from the input image using the aggregated value.