This inventor holds 1 USPTO granted patent. Top assignee: Meta Platforms, Inc.. Active years: 2021.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2021
Title: Mengqian Liu: Advancing Audio-Driven 3D Avatar Rendering.
Introduction
Mengqian Liu is an inventor based in Sunnyvale, California, whose patent work includes technology for creating three-dimensional avatar representations from a person’s voice and facial imagery. He is associated with Meta Platforms, Inc.
Latest Patents
Liu is named on 1 patent: “System and Method for Rendering Three Dimensional Face Model Based on Audio Stream and Image Data.” The invention describes predicting phonemes from an audio stream and translating them into visemes, which represent visible mouth movements associated with speech sounds. It also uses facial image data to determine blendshapes and their weights, forming a 3D avatar model. By synchronizing the visemes with the model over time, the system can produce an animated avatar representation aligned with the person’s speech.
Career Highlights
The patent reflects work at the intersection of speech processing, facial modeling, and computer-generated animation. Its approach combines audio-derived speech movements with image-based facial features to support synchronized 3D avatar rendering.
Collaborations
Liu’s listed coworkers include Evgeny Zatepyakin and Peihong Guo. They are also associated with the patent.
Conclusion
Mengqian Liu’s patent describes a method for bringing together voice and facial imagery to create a synchronized, animated 3D avatar.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile