-
公开(公告)号：US20250086878A1
公开(公告)日：2025-03-13
申请号：US18900362
申请日：2024-09-27
Applicant: Adobe Inc.
Inventor： Kowsheek Mahmood , Kevin Roan , David McKinley Cardwell
Abstract: A method for generating a volume for three-dimensional rendering extracts a plurality of images from a source image input, normalizes the extracted images to have a common pixel size, and determines a notional camera placement for each normalized image to obtain a plurality of annotated normalized images, each annotated with a respective point of view through the view frustum of the notional camera. From the annotated normalized images, the method generates a first volume encompassing a first three-dimensional representation of the target object and selects a smaller subspace within the first volume that encompasses the first three-dimensional representation of the target object. The method generates, from the annotated normalized images, a second volume overlapping the first volume, encompassing a second three-dimensional representation of the target object and having a plurality of voxels, and crops the second volume to limit the second volume to the subspace.
-
公开(公告)号：US12131421B2
公开(公告)日：2024-10-29
申请号：US18083796
申请日：2022-12-19
Applicant: Adobe Inc.
Inventor： Kowsheek Mahmood , Kevin Roan , David McKinley Cardwell
CPC classification number: G06T15/08 , G06T15/50 , G06T19/00 , G06T2210/22 , G06T2219/004
Abstract: A method for generating a volume for three-dimensional rendering extracts a plurality of images from a source image input, normalizes the extracted images to have a common pixel size, and determines a notional camera placement for each normalized image to obtain a plurality of annotated normalized images, each annotated with a respective point of view through the view frustum of the notional camera. From the annotated normalized images, the method generates a first volume encompassing a first three-dimensional representation of the target object and selects a smaller subspace within the first volume that encompasses the first three-dimensional representation of the target object. The method generates, from the annotated normalized images, a second volume overlapping the first volume, encompassing a second three-dimensional representation of the target object and having a plurality of voxels, and crops the second volume to limit the second volume to the subspace.
-
公开(公告)号：US20230274494A1
公开(公告)日：2023-08-31
申请号：US18083796
申请日：2022-12-19
Applicant: Adobe Inc.
Inventor： Kowsheek Mahmood , Kevin Roan , David McKinley Cardwell
CPC classification number: G06T15/08 , G06T19/00 , G06T15/50 , G06T2219/004 , G06T2210/22
Abstract: A method for generating a volume for three-dimensional rendering extracts a plurality of images from a source image input, normalizes the extracted images to have a common pixel size, and determines a notional camera placement for each normalized image to obtain a plurality of annotated normalized images, each annotated with a respective point of view through the view frustum of the notional camera. From the annotated normalized images, the method generates a first volume encompassing a first three-dimensional representation of the target object and selects a smaller subspace within the first volume that encompasses the first three-dimensional representation of the target object. The method generates, from the annotated normalized images, a second volume overlapping the first volume, encompassing a second three-dimensional representation of the target object and having a plurality of voxels, and crops the second volume to limit the second volume to the subspace.
-
-
Search Results
3
records
(took 0.009 seconds)
