-
公开(公告)号：US20230316553A1
公开(公告)日：2023-10-05
申请号：US18205940
申请日：2023-06-05
申请人： Snap Inc.
发明人： Oliver Woodford
CPC分类号： G06T7/55 , G06T5/006 , G06T5/50 , G06T2200/08 , G06T2207/10028
摘要： Aspects of the present disclosure involve a system and a method for performing operations comprising: accessing a source image depicting a target structure; accessing one or more target images depicting at least a portion of the target structure; computing correspondence between a first set of pixels in the source image of a first portion of the target structure and a second set of pixels in the one or more target images of the first portion of the target structure, the correspondence being computed as a function of camera parameters that vary between the source image and the one or more target images; and generating a three-dimensional (3D) model of the target structure based on the correspondence between the first set of pixels in the source image and the second set of pixels in the one or more target images based on a joint optimization of target structure and camera parameters.
-
公开(公告)号：US20230245399A1
公开(公告)日：2023-08-03
申请号：US18131824
申请日：2023-04-06
申请人： Snap Inc.
发明人： Oliver Woodford
CPC分类号： G06T19/006 , G06T7/73 , G06T2200/04 , G06T2207/20084 , G06T2200/08
摘要： A correlation system can be implemented on a user device (e.g., smartphone) to perform image processing tasks e.g., point to point correlations for tasks such as alignment, tracking, and reconstruction of model data. The correlation system can implement normalized cross correlation in a least squares optimization scheme without use of approximations. Normalized cross correlation optimized via least squares can further implement global and local cost functions that are invariant to dynamic lighting conditions.
-
公开(公告)号：US20220084293A1
公开(公告)日：2022-03-17
申请号：US17456487
申请日：2021-11-24
申请人： Snap inc.
发明人： Oliver Woodford
摘要： A correlation system can be implemented on a user device (e.g., smartphone) to perform image processing tasks e.g., point to point correlations for tasks such as alignment, tracking, and reconstruction of model data. The correlation system can implement normalized cross correlation in a least squares optimization scheme without use of approximations. Normalized cross correlation optimized via least squares can further implement global and local cost functions that are invariant to dynamic lighting conditions.
-
公开(公告)号：US20230394681A1
公开(公告)日：2023-12-07
申请号：US18235563
申请日：2023-08-18
申请人： Snap Inc.
发明人： Chen Cao , Menglei Chai , Linjie Luo , Oliver Woodford
IPC分类号： G06T7/246 , G06T13/40 , G06T7/73 , G06V40/16 , G06V10/774
CPC分类号： G06T7/251 , G06T13/40 , G06T7/73 , G06V40/161 , G06V10/774 , G06V40/165 , G06V40/176 , G06V10/62
摘要： Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program and a method for accessing a set of images depicting at least a portion of a face. A set of facial regions of the face is identified, each facial region of the set of facial regions intersecting another facial region with at least one common vertex that is a member of a set of facial vertices. For each facial region of the set of facial regions, a weight formed from a set of region coefficients is generated. Based on the set of facial regions and the weight of each facial region of the set of facial regions, the face is tracked across the set of images.
-
公开(公告)号：US11798213B2
公开(公告)日：2023-10-24
申请号：US17364218
申请日：2021-06-30
申请人： Snap Inc.
CPC分类号： G06T13/00 , G06N3/045 , G06N3/08 , G06T7/20 , G06T11/001 , G06T2207/20081 , G06T2207/20084
摘要： Systems and methods herein describe novel motion representations for animating articulated objects consisting of distinct parts. The described systems and method access source image data, identify driving image data to modify image feature data in the source image sequence data, generate, using an image transformation neural network, modified source image data comprising a plurality of modified source images depicting modified versions of the image feature data, the image transformation neural network being trained to identify, for each image in the source image data, a driving image from the driving image data, the identified driving image being implemented by the image transformation neural network to modify a corresponding source image in the source image data using motion estimation differences between the identified driving image and the corresponding source image, and stores the modified source image data.
-
公开(公告)号：US11769259B2
公开(公告)日：2023-09-26
申请号：US17248908
申请日：2021-02-12
申请人： Snap Inc.
发明人： Chen Cao , Menglei Chai , Linjie Luo , Oliver Woodford
CPC分类号： G06T7/251 , G06T7/73 , G06T13/40 , G06V10/774 , G06V40/161 , G06V40/165 , G06V40/176 , G06V10/62
摘要： Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program and a method for accessing a set of images depicting at least a portion of a face. A set of facial regions of the face is identified, each facial region of the set of facial regions intersecting another facial region with at least one common vertex that is a member of a set of facial vertices. For each facial region of the set of facial regions, a weight formed from a set of region coefficients is generated. Based on the set of facial regions and the weight of each facial region of the set of facial regions, the face is tracked across the set of images.
-
公开(公告)号：US10949648B1
公开(公告)日：2021-03-16
申请号：US16170997
申请日：2018-10-25
申请人： Snap Inc.
发明人： Chen Cao , Menglei Chai , Linjie Luo , Oliver Woodford
摘要： Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program and a method for accessing a set of images depicting at least a portion of a face. A set of facial regions of the face is identified, each facial region of the set of facial regions intersecting another facial region with at least one common vertex which is a member of a set of facial vertices. For each facial region of the set of facial regions, a weight formed from a set of region coefficients is generated. Based on the set of facial regions and the weight of each facial region of the set of facial regions, the face is tracked across the set of images.
-
公开(公告)号：US11710248B2
公开(公告)日：2023-07-25
申请号：US17813887
申请日：2022-07-20
申请人： Snap Inc.
发明人： Oliver Woodford
CPC分类号： G06T7/55 , G06T5/006 , G06T5/50 , G06T2200/08 , G06T2207/10028
摘要： Aspects of the present disclosure involve a system and a method for performing operations comprising: accessing a source image depicting a target structure; accessing one or more target images depicting at least a portion of the target structure; computing correspondence between a first set of pixels in the source image of a first portion of the target structure and a second set of pixels in the one or more target images of the first portion of the target structure, the correspondence being computed as a function of camera parameters that vary between the source image and the one or more target images; and generating a three-dimensional (3D) model of the target structure based on the correspondence between the first set of pixels in the source image and the second set of pixels in the one or more target images based on a joint optimization of target structure and camera parameters.
-
公开(公告)号：US20210407163A1
公开(公告)日：2021-12-30
申请号：US17364218
申请日：2021-06-30
申请人： Snap Inc.
摘要： Systems and methods herein describe novel motion representations for animating articulated objects consisting of distinct parts. The described systems and method access source image data, identify driving image data to modify image feature data in the source image sequence data, generate, using an image transformation neural network, modified source image data comprising a plurality of modified source images depicting modified versions of the image feature data, the image transformation neural network being trained to identify, for each image in the source image data, a driving image from the driving image data, the identified driving image being implemented by the image transformation neural network to modify a corresponding source image in the source image data using motion estimation differences between the identified driving image and the corresponding source image, and stores the modified source image data.
-
公开(公告)号：US20210334993A1
公开(公告)日：2021-10-28
申请号：US16861034
申请日：2020-04-28
申请人： Snap Inc.
发明人： Oliver Woodford
摘要： Aspects of the present disclosure involve a system and a method for performing operations comprising: accessing a source image depicting a target structure; accessing one or more target images depicting at least a portion of the target structure; computing correspondence between a first set of pixels in the source image of a first portion of the target structure and a second set of pixels in the one or more target images of the first portion of the target structure, the correspondence being computed as a function of camera parameters that vary between the source image and the one or more target images; and generating a three-dimensional (3D) model of the target structure based on the correspondence between the first set of pixels in the source image and the second set of pixels in the one or more target images based on a joint optimization of target structure and camera parameters.
-
-
-
-
-
-
-
-
-
搜索结果
20 条记录 (耗时 0.016 秒)
