Jun Saito

US Patent:

20230037339, Feb 9, 2023

Filed:

Jul 26, 2021

Appl. No.:

17/385559

Inventors:

- San Jose CA, US
Jun Saito - Seattle WA, US
Jimei Yang - Mountain View CA, US
Duygu Ceylan Aksit - London, GB
Aaron Hertzmann - San Francisco CA, US

International Classification:

G06T 13/40
G06N 3/04
G06N 20/00
G06K 9/00
G06T 9/00
G06T 7/215

Abstract:

One example method involves a processing device that performs operations that include receiving a request to retarget a source motion into a target object. Operations further include providing the target object to a contact-aware motion retargeting neural network trained to retarget the source motion into the target object. The contact-aware motion retargeting neural network is trained by accessing training data that includes a source object performing the source motion. The contact-aware motion retargeting neural network generates retargeted motion for the target object, based on a self-contact having a pair of input vertices. The retargeted motion is subject to motion constraints that: (i) preserve a relative location of the self-contact and (ii) prevent self-penetration of the target object.

US Patent:

20210375021, Dec 2, 2021

Filed:

May 29, 2020

Appl. No.:

16/888167

Inventors:

- San Jose CA, US
Jun Saito - Seattle WA, US

Assignee:

Adobe Inc. - San Jose CA

International Classification:

G06T 13/40
G06T 13/80
G06N 3/04

Abstract:

Digital character animation automated generation techniques are described that are implemented by an animation generation system via a computing device. These techniques enable the animation generation system to generate an animation of a digital character automatically and without user intervention responsive to a user input of a target action such that the digital character is capable of performing a complex set of actions in a precise and realistic manner within an environment contained within digital content, e.g., an animation as part of a digital video.

US Patent:

20210343059, Nov 4, 2021

Filed:

May 1, 2020

Appl. No.:

16/864724

Inventors:

- San Jose CA, US
Jun Saito - Seattle WA, US
Jimei Yang - Mountain View CA, US
Duygu Ceylan Aksit - San Jose CA, US

Assignee:

Adobe Inc. - San Jose CA

International Classification:

G06T 13/40
G06T 15/20
G06T 15/40
G06N 3/08

Abstract:

Motion retargeting with kinematic constraints is implemented in a digital medium environment. Generally, the described techniques provide for retargeting motion data from a source motion sequence to a target visual object. Accordingly, the described techniques position a target visual object in a defined visual environment to identify kinematic constraints of the target object relative to the visual environment. Further, the described techniques utilize an iterative optimization process that fine tunes the conformance of retargeted motion of a target object to the identified kinematic constraints.

US Patent:

20200265294, Aug 20, 2020

Filed:

Feb 14, 2019

Appl. No.:

16/276559

Inventors:

- San Jose CA, US
Omid Poursaeed - New York NY, US
Jun Saito - Seattle WA, US
Elya Shechtman - Seattle WA, US

Assignee:

Adobe Inc. - San Jose CA

International Classification:

G06N 3/04
G06T 13/00
G06T 17/20
G06N 3/08

Abstract:

In implementations of object animation using generative neural networks, one or more computing devices of a system implement an animation system for reproducing animation of an object in a digital video. A mesh of the object is obtained from a first frame of the digital video and a second frame of the digital video having the object is selected. Features of the object from the second frame are mapped to vertices of the mesh, and the mesh is warped based on the mapping. The warped mesh is rendered as an image by a neural renderer and compared to the object from the second frame to train a neural network. The rendered image is then refined by a generator of a generative adversarial network which includes a discriminator. The discriminator trains the generator to reproduce the object from the second frame as the refined image.

US Patent:

20140375628, Dec 25, 2014

Filed:

Jun 19, 2014

Appl. No.:

14/309433

Inventors:

- Tokyo, JP
Jun Saito - Burbank CA, US

Assignee:

MARZA ANIMATION PLANET, INC. - Tokyo

International Classification:

G06T 13/40

US Classification:

345419

Abstract:

A method for deformation transfer of a source three-dimensional (3D) geometry to a target 3D geometry for computer-implemented blendshapes animation includes solving a linear system equation in which blendshapes deformation transfer with a virtual triangular mesh is performed, where the virtual triangular mesh having a plurality of virtual triangles is assigned to a prescribed region of an animated figure that are presented by a computer-generated mesh, and/or in which blendshapes deformation transfer is performed with Laplacian smoothing.