-
公开(公告)号:US11786129B2
公开(公告)日:2023-10-17
申请号:US17666319
申请日:2022-02-07
Inventor: Srikrishna Karanam , Ziyan Wu , Georgios Georgakis
IPC: G06K9/00 , A61B5/00 , G16H30/40 , G06T7/00 , G06T7/90 , G06T17/00 , G06T7/50 , G06T7/70 , G06T17/20 , G16H10/60 , G16H30/20 , G06V20/64 , G06V40/10 , G06V40/20 , G06V20/62 , G06F18/21 , G06F18/214 , G06V10/764 , G06V10/774 , G06V10/778 , G06V10/82 , G06V10/42 , G06V10/40
CPC classification number: A61B5/0077 , A61B5/0035 , A61B5/70 , G06F18/21 , G06F18/214 , G06F18/2193 , G06T7/0012 , G06T7/50 , G06T7/70 , G06T7/90 , G06T17/00 , G06T17/20 , G06V10/40 , G06V10/42 , G06V10/764 , G06V10/774 , G06V10/7796 , G06V10/82 , G06V20/62 , G06V20/64 , G06V40/10 , G06V40/20 , G16H10/60 , G16H30/20 , G16H30/40 , G06T2200/08 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G06T2207/30004 , G06T2207/30196 , G06V2201/033
Abstract: Human mesh model recovery may utilize prior knowledge of the hierarchical structural correlation between different parts of a human body. Such structural correlation may be between a root kinematic chain of the human body and a head or limb kinematic chain of the human body. Shape and/or pose parameters relating to the human mesh model may be determined by first determining the parameters associated with the root kinematic chain and then using those parameters to predict the parameters associated with the head or limb kinematic chain. Such a task can be accomplished using a system comprising one or more processors and one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to implement one or more neural networks trained to perform functions related to the task.
-
公开(公告)号:US11557391B2
公开(公告)日:2023-01-17
申请号:US16995446
申请日:2020-08-17
Inventor: Ziyan Wu , Srikrishna Karanam , Changjiang Cai , Georgios Georgakis
IPC: G06K9/62 , G16H30/40 , G06T7/00 , G06T7/90 , G06T17/00 , G06T7/50 , G06T7/70 , G06T17/20 , G16H10/60 , G16H30/20 , A61B5/00 , G06V10/40 , G06V10/42 , G06V20/64 , G06V40/10 , G06V40/20 , G06V20/62
Abstract: The pose and shape of a human body may be recovered based on joint location information associated with the human body. The joint location information may be derived based on an image of the human body or from an output of a human motion capture system. The recovery of the pose and shape of the human body may be performed by a computer-implemented artificial neural network (ANN) trained to perform the recovery task using training datasets that include paired joint location information and human model parameters. The training of the ANN may be conducted in accordance with multiple constraints designed to improve the accuracy of the recovery and by artificially manipulating the training data so that the ANN can learn to recover the pose and shape of the human body even with partially observed joint locations.
-
公开(公告)号:US11257586B2
公开(公告)日:2022-02-22
申请号:US16863382
申请日:2020-04-30
Inventor: Srikrishna Karanam , Ziyan Wu , Georgios Georgakis
IPC: G06K9/00 , G16H30/40 , G06T7/00 , G06T7/90 , G06T17/00 , G06K9/46 , G06T7/50 , G06T7/70 , G06K9/62 , G06T17/20 , G16H10/60 , G16H30/20 , A61B5/00 , G06K9/52
Abstract: Human mesh model recovery may utilize prior knowledge of the hierarchical structural correlation between different parts of a human body. Such structural correlation may be between a root kinematic chain of the human body and a head or limb kinematic chain of the human body. Shape and/or pose parameters relating to the human mesh model may be determined by first determining the parameters associated with the root kinematic chain and then using those parameters to predict the parameters associated with the head or limb kinematic chain. Such a task can be accomplished using a system comprising one or more processors and one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to implement one or more neural networks trained to perform functions related to the task.
-
公开(公告)号:US20210158028A1
公开(公告)日:2021-05-27
申请号:US16995446
申请日:2020-08-17
Inventor: Ziyan Wu , Srikrishna Karanam , Changjiang Cai , Georgios Georgakis
Abstract: The pose and shape of a human body may be recovered based on joint location information associated with the human body. The joint location information may be derived based on an image of the human body or from an output of a human motion capture system. The recovery of the pose and shape of the human body may be performed by a computer-implemented artificial neural network (ANN) trained to perform the recovery task using training datasets that include paired joint location information and human model parameters. The training of the ANN may be conducted in accordance with multiple constraints designed to improve the accuracy of the recovery and by artificially manipulating the training data so that the ANN can learn to recover the pose and shape of the human body even with partially observed joint locations.
-
公开(公告)号:US11963741B2
公开(公告)日:2024-04-23
申请号:US18095857
申请日:2023-01-11
Inventor: Ziyan Wu , Srikrishna Karanam , Changjiang Cai , Georgios Georgakis
IPC: G06F18/21 , A61B5/00 , G06F18/214 , G06T7/00 , G06T7/50 , G06T7/70 , G06T7/90 , G06T17/00 , G06T17/20 , G06V10/40 , G06V10/42 , G06V10/764 , G06V10/774 , G06V10/778 , G06V10/82 , G06V20/62 , G06V20/64 , G06V40/10 , G06V40/20 , G16H10/60 , G16H30/20 , G16H30/40
CPC classification number: A61B5/0077 , A61B5/0035 , A61B5/70 , G06F18/21 , G06F18/214 , G06F18/2193 , G06T7/0012 , G06T7/50 , G06T7/70 , G06T7/90 , G06T17/00 , G06T17/20 , G06V10/40 , G06V10/42 , G06V10/764 , G06V10/774 , G06V10/7796 , G06V10/82 , G06V20/62 , G06V20/64 , G06V40/10 , G06V40/20 , G16H10/60 , G16H30/20 , G16H30/40 , G06T2200/08 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G06T2207/30004 , G06T2207/30196 , G06V2201/033
Abstract: The pose and shape of a human body may be recovered based on joint location information associated with the human body. The joint location information may be derived based on an image of the human body or from an output of a human motion capture system. The recovery of the pose and shape of the human body may be performed by a computer-implemented artificial neural network (ANN) trained to perform the recovery task using training datasets that include paired joint location information and human model parameters. The training of the ANN may be conducted in accordance with multiple constraints designed to improve the accuracy of the recovery and by artificially manipulating the training data so that the ANN can learn to recover the pose and shape of the human body even with partially observed joint locations.
-
公开(公告)号:US20230141392A1
公开(公告)日:2023-05-11
申请号:US18095857
申请日:2023-01-11
Inventor: Ziyan Wu , Srikrishna Karanam , Changjiang Cai , Georgios Georgakis
IPC: A61B5/00 , G16H30/40 , G06T7/00 , G06T7/90 , G06T17/00 , G06T7/50 , G06T7/70 , G06T17/20 , G16H10/60 , G16H30/20 , G06V20/64 , G06V40/10 , G06V40/20 , G06V20/62 , G06F18/21 , G06F18/214 , G06V10/764 , G06V10/774 , G06V10/778 , G06V10/82 , G06V10/42 , G06V10/40
CPC classification number: A61B5/0077 , G16H30/40 , G06T7/0012 , G06T7/90 , G06T17/00 , G06T7/50 , G06T7/70 , G06T17/20 , G16H10/60 , G16H30/20 , A61B5/0035 , A61B5/70 , G06V20/64 , G06V40/10 , G06V40/20 , G06V20/62 , G06F18/21 , G06F18/214 , G06F18/2193 , G06V10/764 , G06V10/774 , G06V10/7796 , G06V10/82 , G06V10/42 , G06V10/40 , G06T2207/30004 , G06T2200/08 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G06T2207/30196 , G06V2201/033
Abstract: The pose and shape of a human body may be recovered based on joint location information associated with the human body. The joint location information may be derived based on an image of the human body or from an output of a human motion capture system. The recovery of the pose and shape of the human body may be performed by a computer-implemented artificial neural network (ANN) trained to perform the recovery task using training datasets that include paired joint location information and human model parameters. The training of the ANN may be conducted in accordance with multiple constraints designed to improve the accuracy of the recovery and by artificially manipulating the training data so that the ANN can learn to recover the pose and shape of the human body even with partially observed joint locations.
-
公开(公告)号:US20220165396A1
公开(公告)日:2022-05-26
申请号:US17666319
申请日:2022-02-07
Inventor: Srikrishna Karanam , Ziyan Wu , Georgios Georgakis
IPC: G16H30/40 , G06T7/00 , G06T7/90 , G06T17/00 , G06T7/50 , G06T7/70 , G06K9/62 , G06T17/20 , G16H10/60 , G16H30/20 , A61B5/00 , G06V10/40 , G06V10/42 , G06V20/64 , G06V40/10 , G06V40/20
Abstract: Human mesh model recovery may utilize prior knowledge of the hierarchical structural correlation between different parts of a human body. Such structural correlation may be between a root kinematic chain of the human body and a head or limb kinematic chain of the human body. Shape and/or pose parameters relating to the human mesh model may be determined by first determining the parameters associated with the root kinematic chain and then using those parameters to predict the parameters associated with the head or limb kinematic chain. Such a task can be accomplished using a system comprising one or more processors and one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to implement one or more neural networks trained to perform functions related to the task.
-
公开(公告)号:US20210158107A1
公开(公告)日:2021-05-27
申请号:US16863382
申请日:2020-04-30
Inventor: Srikrishna Karanam , Ziyan Wu , Georgios Georgakis
Abstract: Human mesh model recovery may utilize prior knowledge of the hierarchical structural correlation between different parts of a human body. Such structural correlation may be between a root kinematic chain of the human body and a head or limb kinematic chain of the human body. Shape and/or pose parameters relating to the human mesh model may be determined by first determining the parameters associated with the root kinematic chain and then using those parameters to predict the parameters associated with the head or limb kinematic chain. Such a task can be accomplished using a system comprising one or more processors and one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to implement one or more neural networks trained to perform functions related to the task.
-
-
-
-
-
-
-