-
公开(公告)号：US20220292697A1
公开(公告)日：2022-09-15
申请号：US17825994
申请日：2022-05-26
Applicant: Snap Inc.
Inventor： Shenlong Wang , Linjie Luo , Ning Zhang , Jia Li
Abstract: Dense feature scale detection can be implemented using multiple convolutional neural networks trained on scale data to more accurately and efficiently match pixels between images. An input image can be used to generate multiple scaled images. The multiple scaled images are input into a feature net, which outputs feature data for the multiple scaled images. An attention net is used to generate an attention map from the input image. The attention map assigns emphasis as a soft distribution to different scales based on texture analysis. The feature data and the attention data can be combined through a multiplication process and then summed to generate dense features for comparison.
-
公开(公告)号：US10552968B1
公开(公告)日：2020-02-04
申请号：US15712990
申请日：2017-09-22
Applicant: Snap Inc.
Inventor： Shenlong Wang , Linjie Luo , Ning Zhang , Jia Li
Abstract: Dense feature scale detection can be implemented using multiple convolutional neural networks trained on scale data to more accurately and efficiently match pixels between images. An input image can be used to generate multiple scaled images. The multiple scaled images are input into a feature net, which outputs feature data for the multiple scaled images. An attention net is used to generate an attention map from the input image. The attention map assigns emphasis as a soft distribution to different scales based on texture analysis. The feature data and the attention data can be combined through a multiplication process and then summed to generate dense features for comparison.
-
公开(公告)号：US12198357B2
公开(公告)日：2025-01-14
申请号：US18367034
申请日：2023-09-12
Applicant: Snap Inc.
Inventor： Shenlong Wang , Linjie Luo , Ning Zhang , Jia Li
Abstract: Dense feature scale detection can be implemented using multiple convolutional neural networks trained on scale data to more accurately and efficiently match pixels between images. An input image can be used to generate multiple scaled images. The multiple scaled images are input into a feature net, which outputs feature data for the multiple scaled images. An attention net is used to generate an attention map from the input image. The attention map assigns emphasis as a soft distribution to different scales based on texture analysis. The feature data and the attention data can be combined through a multiplication process and then summed to generate dense features for comparison.
-
公开(公告)号：US11367205B1
公开(公告)日：2022-06-21
申请号：US16721483
申请日：2019-12-19
Applicant: Snap Inc.
Inventor： Shenlong Wang , Linjie Luo , Ning Zhang , Jia Li
Abstract: Dense feature scale detection can be implemented using multiple convolutional neural networks trained on scale data to more accurately and efficiently match pixels between images. An input image can be used to generate multiple scaled images. The multiple scaled images are input into a feature net, which outputs feature data for the multiple scaled images. An attention net is used to generate an attention map from the input image. The attention map assigns emphasis as a soft distribution to different scales based on texture analysis. The feature data and the attention data can be combined through a multiplication process and then summed to generate dense features for comparison.
-
公开(公告)号：US20200258248A1
公开(公告)日：2020-08-13
申请号：US16859468
申请日：2020-04-27
Applicant: Snap Inc.
Inventor： Kun Duan , Daniel Ron , Chongyang Ma , Ning Xu , Shenlong Wang , Sumant Milind Hanumante , Dhritiman Sagar
Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.
-
Patent Agency Ranking
公开(公告)号：US11861854B2
公开(公告)日：2024-01-02
申请号：US17825994
申请日：2022-05-26
Applicant: Snap Inc.
Inventor： Shenlong Wang , Linjie Luo , Ning Zhang , Jia Li
CPC classification number: G06T7/248 , G06T7/33 , G06V10/454 , G06V10/764 , G06V10/82 , G06T7/40 , G06T2207/20084
Abstract: Dense feature scale detection can be implemented using multiple convolutional neural networks trained on scale data to more accurately and efficiently match pixels between images. An input image can be used to generate multiple scaled images. The multiple scaled images are input into a feature net, which outputs feature data for the multiple scaled images. An attention net is used to generate an attention map from the input image. The attention map assigns emphasis as a soft distribution to different scales based on texture analysis. The feature data and the attention data can be combined through a multiplication process and then summed to generate dense features for comparison.
-
公开(公告)号：US20230419512A1
公开(公告)日：2023-12-28
申请号：US18367034
申请日：2023-09-12
Applicant: Snap Inc.
Inventor： Shenlong Wang , Linjie Luo , Ning Zhang , Jia Li
IPC: G06T7/246 , G06T7/33 , G06V10/764 , G06V10/82 , G06V10/44
CPC classification number: G06T7/248 , G06T7/33 , G06V10/764 , G06V10/82 , G06V10/454 , G06T2207/20084 , G06T7/40
Abstract: Dense feature scale detection can be implemented using multiple convolutional neural networks trained on scale data to more accurately and efficiently match pixels between images. An input image can be used to generate multiple scaled images. The multiple scaled images are input into a feature net, which outputs feature data for the multiple scaled images. An attention net is used to generate an attention map from the input image. The attention map assigns emphasis as a soft distribution to different scales based on texture analysis. The feature data and the attention data can be combined through a multiplication process and then summed to generate dense features for comparison.
-
公开(公告)号：US11715223B2
公开(公告)日：2023-08-01
申请号：US17589459
申请日：2022-01-31
Applicant: Snap Inc.
Inventor： Kun Duan , Daniel Ron , Chongyang Ma , Ning Xu , Shenlong Wang , Sumant Milind Hanumante , Dhritiman Sagar
CPC classification number: G06T7/536 , G06T11/60 , G06T2207/10028 , G06T2207/20081 , G06T2207/20084
Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.
-
公开(公告)号：US20220156956A1
公开(公告)日：2022-05-19
申请号：US17589459
申请日：2022-01-31
Applicant: Snap Inc.
Inventor： Kun Duan , Daniel Ron , Chongyang Ma , Ning Xu , Shenlong Wang , Sumant Milind Hanumante , Dhritiman Sagar
Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.
-
公开(公告)号：US11276190B2
公开(公告)日：2022-03-15
申请号：US16859468
申请日：2020-04-27
Applicant: Snap Inc.
Inventor： Kun Duan , Daniel Ron , Chongyang Ma , Ning Xu , Shenlong Wang , Sumant Milind Hanumante , Dhritiman Sagar
Abstract: An active depth detection system can generate a depth map from an image and user interaction data, such as a pair of clicks. The active depth detection system can be implemented as a recurrent neural network that can receive the user interaction data as runtime inputs after training. The active depth detection system can store the generated depth map for further processing, such as image manipulation or real-world object detection.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.014 seconds)
