公开(公告)号：US20190304152A1

公开(公告)日：2019-10-03

申请号：US16364866

申请日：2019-03-26

Applicant: Samsung Electronics Co., Ltd.

Inventor： Albert SAÀ-GARRIGA ,  Karthikeyan SARAVANAN ,  Alessandro VANDINI ,  Antoine LARRECHE ,  Daniel ANSORREGUI

IPC: G06T11/60 ,  G06K9/00 ,  G06K9/62 ,  G06T5/00 ,  G06T5/10

Abstract: An image processing method is provided. The image processing method includes detecting a face of an object present on an image, obtaining at least one feature from the detected face as at least one facial parameter and obtaining at least one context related to the image as at least one contextual parameter, determining a manipulation point for manipulating the detected face, based on the obtained at least one facial parameter and the obtained at least one contextual parameter, and manipulating the image based on the determined manipulation point.

公开(公告)号：US20230114028A1

公开(公告)日：2023-04-13

申请号：US17960571

申请日：2022-10-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Mehmet YUCEL ,  Albert SAÀ-GARRIGA ,  Valia DIMARIDOU

IPC: G06T7/50 ,  G06V10/74 ,  G06V10/776

Abstract: Broadly speaking, this disclosure generally relates to methods, systems and apparatuses for performing monocular depth estimation, i.e. depth estimation using a single camera. In particular, this disclosure relates to a method for generating a training dataset for training a machine learning, ML, model using federated learning to perform depth estimation. Advantageously, the method to generate a training dataset enables a diverse training dataset to be generated while maintaining user data privacy. This disclosure also provides methods for training the ML model using the generated training dataset. Advantageously, the methods determine whether a community ML model that is trained by client devices needs to be retrained, and/or whether a global ML model, which is used to generate the community ML model, needs to be retrained.