US 11,948,376 B2
Method, system, and device of generating a reduced-size volumetric dataset
Amit Chachek, Closter, NJ (US)
Assigned to REALMOTION INC., New York, NY (US)
Filed by REALMOTION INC., New York, NY (US)
Filed on Jun. 25, 2023, as Appl. No. 18/213,846.
Application 18/213,846 is a continuation of application No. 18/059,099, filed on Nov. 28, 2022, granted, now 11,721,114.
Application 18/059,099 is a continuation of application No. 17/478,919, filed on Sep. 19, 2021, granted, now 11,514,646, issued on Nov. 29, 2022.
Application 17/478,919 is a continuation of application No. 16/773,994, filed on Jan. 28, 2020, granted, now 11,127,206, issued on Sep. 21, 2021.
Claims priority of provisional application 62/797,961, filed on Jan. 29, 2019.
Prior Publication US 2023/0334881 A1, Oct. 19, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 17/20 (2006.01); G06F 18/22 (2023.01); G06T 7/20 (2017.01); G06T 13/40 (2011.01); G06T 15/08 (2011.01); G06T 17/10 (2006.01); G06T 19/20 (2011.01); G06V 10/75 (2022.01); G06V 20/64 (2022.01); G06V 40/20 (2022.01)
CPC G06V 20/653 (2022.01) [G06F 18/22 (2023.01); G06T 7/20 (2013.01); G06T 13/40 (2013.01); G06T 15/08 (2013.01); G06T 17/10 (2013.01); G06T 17/20 (2013.01); G06T 17/205 (2013.01); G06T 19/20 (2013.01); G06V 10/754 (2022.01); G06V 40/23 (2022.01); G06T 2200/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
(a) receiving a plurality of three-dimensional volumetric datasets that correspond to a particular object;
(b) generating, from said plurality of three-dimensional volumetric datasets, a single uniform mesh dataset that corresponds to said particular object;
wherein a size of said single uniform mesh dataset is less than ¼ of an aggregate size of said plurality of three-dimensional volumetric datasets;
wherein the generating comprises:
adding a virtual differentiator feature into a particular portion of said particular object, which is spatially tracked over time and across frames, to improve correctness of computer-based tracking of said particular object as it is being animated or redressed;
wherein adding the virtual differentiator feature is performed by one or more operations selected from the group consisting of:
(I) adding a particular texture to said particular portion of said particular object,
(II) adding a particular layer said particular portion of said particular object,
(III) adding one or more particular vectors to particular portion of said particular object,
(IV) adding one or more particular data-points to said particular portion of said particular object from a different angle;
wherein the added virtual differentiator feature is used to perform at least one of:
(A) distinguishing among two or more portions of a volumetric dataset;
(B) distinguishing among two or more portions of a three-dimensional representation that corresponds to two or more regions of the particular object that are visually identical to each other;
(C) distinguishing among two or more portions of a three-dimensional representation that corresponds to two or more regions of the particular object that are similar to each other but are not identical to each other;
(D) enabling temporal-coherence uniform topology in applying an animation effect to said particular object;
(E) enabling temporal-coherence uniform topology in applying a texture effect to said particular object.