San Mateo, CA, United States of America

Kangle Deng

This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Roblox Corporation. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Kangle Deng. Retrieved from https://idiyas.com/inventor/kangle-deng-yrermzpb

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank
USPTO Granted Patents = 1 

% Patents Active = 100.0

Average Co-Inventor Count = 7.0

ph-index = 1


Company Filing History:


Years Active: 2026

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Kangle Deng and View-Consistent Texture Generation

Introduction

Kangle Deng is an inventor based in San Mateo, California, and is associated with Roblox Corporation. His work includes an invention for generating view-consistent textures for three-dimensional objects using generative machine learning.

Latest Patents

Deng is credited with 1 patent: “View Consistent Texture Generation for Three Dimensional Objects.” The invention describes methods, systems, and computer-readable media for creating textures that remain consistent across different views of a 3D object.

The method generates multiple depth maps from a 3D mesh, with each map corresponding to a view of the object. It then uses the depth maps and a text prompt describing the desired texture as inputs to a generative machine-learning model, which produces two or more views of a texture map. Those views partially cover the mesh and are combined in relation to the mesh to create the final texture map.

Career Highlights

Deng’s listed patent connects generative machine learning with 3D modeling and texture creation. The approach is designed to help produce coherent textures across multiple perspectives of a three-dimensional object.

Collaborations

Deng’s listed coworkers include Victor B. Zordan and Timothy Paul Omernick. The available information identifies them as coworkers but does not specify their roles in the patent.

Conclusion

Kangle Deng’s patent presents a machine-learning approach to generating textures that remain consistent across views, reflecting work at the intersection of 3D graphics and generative technology.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…