-
Patent Agency Ranking
公开(公告)号：US20210272253A1
公开(公告)日：2021-09-02
申请号：US16803332
申请日：2020-02-27
Applicant: Adobe Inc.
Inventor： Zhe Lin , Vipul Dalal , Vera Lychagina , Shabnam Ghadar , Saeid Motiian , Rohith mohan Dodle , Prethebha Chandrasegaran , Mina Doroudi , Midhun Harikumar , Kannan Iyer , Jayant Kumar , Gaurav Kukal , Daniel Miranda , Charles R. McKinney , Archit Kalra
Abstract: The present disclosure relates to an image merging system that automatically and seamlessly detects and merges missing people for a set of digital images into a composite group photo. For instance, the image merging system utilizes a number of models and operations to automatically analyze multiple digital images to identify a missing person from a base image, segment the missing person from the second image, and generate a composite group photo by merging the segmented image of the missing person into the base image. In this manner, the image merging system automatically creates merged group photos that appear natural and realistic.
-
公开(公告)号：US12067499B2
公开(公告)日：2024-08-20
申请号：US17087116
申请日：2020-11-02
Applicant: Adobe Inc.
Inventor： Akhilesh Kumar , Xiaozhen Xue , Daniel Miranda , Nicolas Huynh Thien , Kshitiz Garg
Abstract: This disclosure describes one or more implementations of a video inference system that utilizes machine-learning models to efficiently and flexibly process digital videos utilizing various improved video inference architectures. For example, the video inference system provides a framework for improving digital video processing by increasing the efficiency of both central processing units (CPUs) and graphics processing units (GPUs). In one example, the video inference system utilizes a first video inference architecture to reduce the number of computing resources needed to inference digital videos by analyzing multiple digital videos utilizing sets of CPU/GPU containers along with parallel pipeline processing. In a further example, the video inference system utilizes a second video inference architecture that facilitates multiple CPUs to preprocess multiple digital videos in parallel as well as a GPU to continuously, sequentially, and efficiently inference each of the digital videos.
-
公开(公告)号：US20240362506A1
公开(公告)日：2024-10-31
申请号：US18771409
申请日：2024-07-12
Applicant: Adobe Inc.
Inventor： Akhilesh Kumar , Xiaozhen Xue , Daniel Miranda , Nicolas Huynh Thien , Kshitiz Garg
Abstract: This disclosure describes one or more implementations of a video inference system that utilizes machine-learning models to efficiently and flexibly process digital videos utilizing various improved video inference architectures. For example, the video inference system provides a framework for improving digital video processing by increasing the efficiency of both central processing units (CPUs) and graphics processing units (GPUs). In one example, the video inference system utilizes a first video inference architecture to reduce the number of computing resources needed to inference digital videos by analyzing multiple digital videos utilizing sets of CPU/GPU containers along with parallel pipeline processing. In a further example, the video inference system utilizes a second video inference architecture that facilitates multiple CPUs to preprocess multiple digital videos in parallel as well as a GPU to continuously, sequentially, and efficiently inference each of the digital videos.
-
公开(公告)号：US11574392B2
公开(公告)日：2023-02-07
申请号：US16803332
申请日：2020-02-27
Applicant: Adobe Inc.
Inventor： Zhe Lin , Vipul Dalal , Vera Lychagina , Shabnam Ghadar , Saeid Motiian , Rohith mohan Dodle , Prethebha Chandrasegaran , Mina Doroudi , Midhun Harikumar , Kannan Iyer , Jayant Kumar , Gaurav Kukal , Daniel Miranda , Charles R McKinney , Archit Kalra
Abstract: The present disclosure relates to an image merging system that automatically and seamlessly detects and merges missing people for a set of digital images into a composite group photo. For instance, the image merging system utilizes a number of models and operations to automatically analyze multiple digital images to identify a missing person from a base image, segment the missing person from the second image, and generate a composite group photo by merging the segmented image of the missing person into the base image. In this manner, the image merging system automatically creates merged group photos that appear natural and realistic.
-
公开(公告)号：US20220138596A1
公开(公告)日：2022-05-05
申请号：US17087116
申请日：2020-11-02
Applicant: Adobe Inc.
Inventor： Akhilesh Kumar , Xiaozhen Xue , Daniel Miranda , Nicolas Huynh Thien , Kshitiz Garg
Abstract: This disclosure describes one or more implementations of a video inference system that utilizes machine-learning models to efficiently and flexibly process digital videos utilizing various improved video inference architectures. For example, the video inference system provides a framework for improving digital video processing by increasing the efficiency of both central processing units (CPUs) and graphics processing units (GPUs). In one example, the video inference system utilizes a first video inference architecture to reduce the number of computing resources needed to inference digital videos by analyzing multiple digital videos utilizing sets of CPU/GPU containers along with parallel pipeline processing. In a further example, the video inference system utilizes a second video inference architecture that facilitates multiple CPUs to preprocess multiple digital videos in parallel as well as a GPU to continuously, sequentially, and efficiently inference each of the digital videos.
-
-
-
-
Search Results
5
records
(took 0.015 seconds)
