-
公开(公告)号：US20200013219A1
公开(公告)日：2020-01-09
申请号：US16573157
申请日：2019-09-17
Applicant: A9.com, Inc.
Inventor： Arnab Sanat Kumar Dhua , Himanshu Arora , Radek Grzeszczuk
Abstract: Objects can be rendered in three-dimensions and viewed and manipulated in an augmented reality environment. Background images are subtracted from object images from multiple viewpoints to provide baseline representations of the object. Morphological operations can be used to remove errors caused by misalignment of an object image and background image. Using two different contrast thresholds, pixels can be identified that can be said at two different confidence levels to be object pixels. An edge detection algorithm can be used to determine object contours. Low confidence pixels can be associated with the object if they can be connected to high confidence pixels without crossing an object contour. Segmentation masks can be created from high confidence pixels and properly associated low confidence pixels. Segmentation masks can be used to create a three-dimensional representation of the object.
-
公开(公告)号：US10593066B1
公开(公告)日：2020-03-17
申请号：US15866177
申请日：2018-01-09
Applicant: A9.com, Inc.
Inventor： Arnab Sanat Kumar Dhua , Neil Raj Kumar , Karl Hillesland , Radek Grzeszczuk , Scott Paul Robertson
Abstract: Objects can be rendered in three dimensions and viewed and manipulated in an augmented reality environment. A number of object images, a number of segmentation masks, and an object mesh structure are used by a client device to render the object in three dimensions. The object images and segmentation masks can be sequenced into frames. The object images and segmentation masks can be partitioned into patches and sequenced, or ordered, within each patch, and a keyframe can be assigned in each patch. Then, the object images and segmentation masks can be encoded into video files and sent to a client device. The client device can quickly retrieve a requested object image and segmentation mask based at least in part on identifying the keyframe in the same patch as the object image and segmentation mask.
-
公开(公告)号：US11776211B2
公开(公告)日：2023-10-03
申请号：US17181885
申请日：2021-02-22
Applicant: A9.com, Inc.
Inventor： Karl Hillesland , Xi Zhang , Himanshu Arora , Yu Lou , Radek Grzeszczuk , Arnab Sanat Kumar Dhua
CPC classification number: G06T17/20 , G06T7/70 , G06T7/97 , G06T19/003
Abstract: Images of various views of objects can be captured. An object mesh structure can be created based at least in part on the object images. The object mesh structure represents the three-dimensional shape of the object. Alpha masks indicating which pixels are associated with the object can be used to refine the object mesh structure. A request can be made to view the object from an arbitrary viewpoint which differs from the viewpoints associated with the captured images. A subset of the captured images can be used to create a synthetic image. Different weights can be assigned to the captured image to render a synthetic image that represents the view from the arbitrary viewpoint selected. The input images for the synthetic image can be prefetched, or loaded into memory before the arbitrary view is requested. The images can also be cached for future use or to avoid reloading them for another synthetic image.
-
公开(公告)号：US20210174586A1
公开(公告)日：2021-06-10
申请号：US17181885
申请日：2021-02-22
Applicant: A9.com, Inc.
Inventor： Karl Hillesland , Xi Zhang , Himanshu Arora , Yu Lou , Radek Grzeszczuk , Arnab Sanat Kumar Dhua
Abstract: Images of various views of objects can be captured. An object mesh structure can be created based at least in part on the object images. The object mesh structure represents the three-dimensional shape of the object. Alpha masks indicating which pixels are associated with the object can be used to refine the object mesh structure. A request can be made to view the object from an arbitrary viewpoint which differs from the viewpoints associated with the captured images. A subset of the captured images can be used to create a synthetic image. Different weights can be assigned to the captured image to render a synthetic image that represents the view from the arbitrary viewpoint selected. The input images for the synthetic image can be prefetched, or loaded into memory before the arbitrary view is requested. The images can also be cached for future use or to avoid reloading them for another synthetic image.
-
公开(公告)号：US10950043B1
公开(公告)日：2021-03-16
申请号：US15944717
申请日：2018-04-03
Applicant: A9.com, Inc.
Inventor： Karl Hillesland , Xi Zhang , Himanshu Arora , Yu Lou , Radek Grzeszczuk , Arnab Sanat Kumar Dhua
Abstract: Images of various views of objects can be captured. An object mesh structure can be created based at least in part on the object images. The object mesh structure represents the three-dimensional shape of the object. Alpha masks indicating which pixels are associated with the object can be used to refine the object mesh structure. A request can be made to view the object from an arbitrary viewpoint which differs from the viewpoints associated with the captured images. A subset of the captured images can be used to create a synthetic image. Different weights can be assigned to the captured image to render a synthetic image that represents the view from the arbitrary viewpoint selected. The input images for the synthetic image can be prefetched, or loaded into memory before the arbitrary view is requested. The images can also be cached for future use or to avoid reloading them for another synthetic image.
-
Patent Agency Ranking
公开(公告)号：US10665015B2
公开(公告)日：2020-05-26
申请号：US16573157
申请日：2019-09-17
Applicant: A9.com, Inc.
Inventor： Arnab Sanat Kumar Dhua , Himanshu Arora , Radek Grzeszczuk
Abstract: Objects can be rendered in three-dimensions and viewed and manipulated in an augmented reality environment. Background images are subtracted from object images from multiple viewpoints to provide baseline representations of the object. Morphological operations can be used to remove errors caused by misalignment of an object image and background image. Using two different contrast thresholds, pixels can be identified that can be said at two different confidence levels to be object pixels. An edge detection algorithm can be used to determine object contours. Low confidence pixels can be associated with the object if they can be connected to high confidence pixels without crossing an object contour. Segmentation masks can be created from high confidence pixels and properly associated low confidence pixels. Segmentation masks can be used to create a three-dimensional representation of the object.
-
公开(公告)号：US20190266797A1
公开(公告)日：2019-08-29
申请号：US16411642
申请日：2019-05-14
Applicant: A9.com, Inc.
Inventor： Arnab Sanat Kumar Dhua , Himanshu Arora , Radek Grzeszczuk
Abstract: Objects can be rendered in three-dimensions and viewed and manipulated in an augmented reality environment. Background images are subtracted from object images from multiple viewpoints to provide baseline representations of the object. Morphological operations can be used to remove errors caused by misalignment of an object image and background image. Using two different contrast thresholds, pixels can be identified that can be said at two different confidence levels to be object pixels. An edge detection algorithm can be used to determine object contours. Low confidence pixels can be associated with the object if they can be connected to high confidence pixels without crossing an object contour. Segmentation masks can be created from high confidence pixels and properly associated low confidence pixels. Segmentation masks can be used to create a three-dimensional representation of the object.
-
公开(公告)号：US10347045B1
公开(公告)日：2019-07-09
申请号：US15824697
申请日：2017-11-28
Applicant: A9.com, Inc.
Inventor： Arnab Sanat Kumar Dhua , Himanshu Arora , Radek Grzeszczuk
Abstract: Objects can be rendered in three-dimensions and viewed and manipulated in an augmented reality environment. Background images are subtracted from object images from multiple viewpoints to provide baseline representations of the object. Morphological operations can be used to remove errors caused by misalignment of an object image and background image. Using two different contrast thresholds, pixels can be identified that can be said at two different confidence levels to be object pixels. An edge detection algorithm can be used to determine object contours. Low confidence pixels can be associated with the object if they can be connected to high confidence pixels without crossing an object contour. Segmentation masks can be created from high confidence pixels and properly associated low confidence pixels. Segmentation masks can be used to create a three-dimensional representation of the object.
-
公开(公告)号：US10943370B2
公开(公告)日：2021-03-09
申请号：US16808247
申请日：2020-03-03
Applicant: A9.com, Inc.
Inventor： Arnab Sanat Kumar Dhua , Neil Raj Kumar , Karl Hillesland , Radek Grzeszczuk , Scott Paul Robertson
Abstract: Objects can be rendered in three dimensions and viewed and manipulated in an augmented reality environment. A number of object images, a number of segmentation masks, and an object mesh structure are used by a client device to render the object in three dimensions. The object images and segmentation masks can be sequenced into frames. The object images and segmentation masks can be partitioned into patches and sequenced, or ordered, within each patch, and a keyframe can be assigned in each patch. Then, the object images and segmentation masks can be encoded into video files and sent to a client device. The client device can quickly retrieve a requested object image and segmentation mask based at least in part on identifying the keyframe in the same patch as the object image and segmentation mask.
-
公开(公告)号：US10453254B2
公开(公告)日：2019-10-22
申请号：US16411642
申请日：2019-05-14
Applicant: A9.com, Inc.
Inventor： Arnab Sanat Kumar Dhua , Himanshu Arora , Radek Grzeszczuk
Abstract: Objects can be rendered in three-dimensions and viewed and manipulated in an augmented reality environment. Background images are subtracted from object images from multiple viewpoints to provide baseline representations of the object. Morphological operations can be used to remove errors caused by misalignment of an object image and background image. Using two different contrast thresholds, pixels can be identified that can be said at two different confidence levels to be object pixels. An edge detection algorithm can be used to determine object contours. Low confidence pixels can be associated with the object if they can be connected to high confidence pixels without crossing an object contour. Segmentation masks can be created from high confidence pixels and properly associated low confidence pixels. Segmentation masks can be used to create a three-dimensional representation of the object.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.019 seconds)
