-
公开(公告)号：US20220292314A1
公开(公告)日：2022-09-15
申请号：US17200643
申请日：2021-03-12
Applicant: Google LLC
Inventor： Cristian Sminchisescu , Andrei Zanfir , Eduard Gabriel Bazavan , Mihai Zanfir , William Tafel Freeman , Rahul Sukthankar
Abstract: Systems and methods are directed to a method for estimation of an object state from image data. The method can include obtaining two-dimensional image data depicting an object. The method can include processing, with an estimation portion of a machine-learned object state estimation model, the two-dimensional image data to obtain an initial estimated state of the object. The method can include, for each of one or more refinement iterations, obtaining a previous loss value associated with a previous estimated state for the object, processing the previous loss value to obtain a current estimated state of the object, and evaluating a loss function to determine a loss value associated with the current estimated state of the object. The method can include providing a final estimated state for the object.
-
公开(公告)号：US11908071B2
公开(公告)日：2024-02-20
申请号：US17495960
申请日：2021-10-07
Applicant: Google LLC
Inventor： Cristian Sminchisescu , Mihai Zanfir , Andrei Zanfir , Eduard Gabriel Bazavan , William Tafel Freeman , Rahul Sukthankar
CPC classification number: G06T17/00 , G06N3/08 , G06N20/00 , G06T11/003 , G06T2207/20081
Abstract: The present disclosure is generally directed to reconstructing representations of bodies from images. An example method of the present disclosure includes inputting, into a machine-learned reconstruction model, input data descriptive of an image depicting a body; predicting, using a machine-learned marker prediction component of the reconstruction model, a set of surface marker locations on the body; and outputting, using a machine-learned marker poser component of the reconstruction model, an output representation of the body that corresponds to the set of surface marker locations. In the example method, one or more parameters of the reconstruction model were learned at least in part based on a consistency loss corresponding to a distance between relaxed-constraint representations generated from a prior set of surface marker locations predicted according to the one or more parameters and parametric representations generated from the prior set using kinematic constraints associated with the body.
-
公开(公告)号：US11836221B2
公开(公告)日：2023-12-05
申请号：US17200643
申请日：2021-03-12
Applicant: Google LLC
Inventor： Cristian Sminchisescu , Andrei Zanfir , Eduard Gabriel Bazavan , Mihai Zanfir , William Tafel Freeman , Rahul Sukthankar
CPC classification number: G06F18/217 , G06N3/08 , G06T7/73 , G06V40/103 , G06T2207/20081 , G06T2207/20084 , G06T2207/30196
Abstract: Systems and methods are directed to a method for estimation of an object state from image data. The method can include obtaining two-dimensional image data depicting an object. The method can include processing, with an estimation portion of a machine-learned object state estimation model, the two-dimensional image data to obtain an initial estimated state of the object. The method can include, for each of one or more refinement iterations, obtaining a previous loss value associated with a previous estimated state for the object, processing the previous loss value to obtain a current estimated state of the object, and evaluating a loss function to determine a loss value associated with the current estimated state of the object. The method can include providing a final estimated state for the object.
-
公开(公告)号：US20230116884A1
公开(公告)日：2023-04-13
申请号：US17495960
申请日：2021-10-07
Applicant: Google LLC
Inventor： Cristian Sminchisescu , Mihai Zanfir , Andrei Zanfir , Eduard Gabriel Bazavan , William Tafel Freeman , Rahul Sukthankar
Abstract: The present disclosure is generally directed to reconstructing representations of bodies from images. An example method of the present disclosure includes inputting, into a machine-learned reconstruction model, input data descriptive of an image depicting a body; predicting, using a machine-learned marker prediction component of the reconstruction model, a set of surface marker locations on the body; and outputting, using a machine-learned marker poser component of the reconstruction model, an output representation of the body that corresponds to the set of surface marker locations. In the example method, one or more parameters of the reconstruction model were learned at least in part based on a consistency loss corresponding to a distance between relaxed-constraint representations generated from a prior set of surface marker locations predicted according to the one or more parameters and parametric representations generated from the prior set using kinematic constraints associated with the body.
-
-
-
Search Results
4
records
(took 0.012 seconds)
