IDiyas

For the Inventor, By the Inventor

Seattle, WA, United States of America

Jun Saito

USPTO Granted Patents = 13 

Average Co-Inventor Count = 3.7

ph-index = 2

Forward Citations = 19(Granted Patents)


Company Filing History:

goldMedal13 out of 6,898 
 
Adobe, Inc.
 patents

Years Active: 2020-2025

where 'Filed Patents' based on already Granted Patents

13 patents (USPTO):
1. 12347135 - Generating gesture reenactment video from video motion graphs using machine learning (2025-07-01),
2. 12347034 - Generating mappings of three-dimensional meshes utilizing neural network gradient fields (2025-07-01),
3. 12067661 - Generating human motion sequences utilizing unsupervised learning of discretized features via a neural network encoder-decoder (2024-08-20),
4. 12033261 - Contact-aware retargeting of motion (2024-07-09),
5. 11861779 - Digital object animation using control points (2024-01-02),
6. 11682238 - Re-timing a video sequence to an audio sequence based on motion and audio beat detection (2023-06-20),
7. 11625881 - Motion retargeting with kinematic constraints (2023-04-11),
8. 11531697 - Identifying and providing digital images depicting human poses utilizing visual interactive content search and virtual mannequins (2022-12-20),
9. 11321895 - Neural state machine digital character animation (2022-05-03),
10. 11257269 - Inverse kinematic solution blending in digital character animation (2022-02-22),
11. 11170551 - Motion retargeting with kinematic constraints (2021-11-09),
12. 10977549 - Object animation using generative neural networks (2021-04-13),
13. 10818065 - Inverse kinematic solution blending in digital character animation (2020-10-27),

Title: Innovations by Jun Saito

Introduction

Jun Saito is a prominent inventor based in Seattle, WA, known for his significant contributions to technology and innovation. With a total of 13 patents to his name, Saito has made remarkable advancements in the fields of neural networks and machine learning.

Latest Patents

One of Saito's latest patents involves generating mappings of three-dimensional meshes utilizing neural network gradient fields. This patent discloses methods, systems, and non-transitory computer-readable storage media for generating digital chain pull paintings in digital images. The system generates a plurality of matrices over an ambient space for polygons of a three-dimensional mesh based on various features associated with those polygons. It determines a gradient field based on these matrices and generates a mapping for the three-dimensional mesh based on the gradient field and a differential operator corresponding to the mesh.

Another notable patent focuses on generating gesture reenactment videos from video motion graphs using machine learning. This invention outlines a process for creating a gesture reenactment video sequence that corresponds to a target audio sequence. The system receives a reference speech video and generates a video motion graph representing it. It then identifies a node path through the video motion graph based on target audio features and generates an output media sequence paired with the target audio.

Career Highlights

Jun Saito is currently employed at Adobe, Inc., where he continues to innovate and develop cutting-edge technologies. His work at Adobe has allowed him to explore various applications of his inventions in the realm of digital media and graphics.

Collaborations

Saito has collaborated with notable coworkers, including Jimei Yang and Ruben Eduardo Villegas, contributing to a dynamic and innovative work environment.

Conclusion

Jun Saito's contributions to technology through his patents and work at Adobe, Inc. highlight his role as a leading inventor in the field. His innovative approaches to neural networks and machine learning continue to shape the future of digital media.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…