Microsoft technology licensing, llc (20240127522). MULTI-MODAL THREE-DIMENSIONAL FACE MODELING AND TRACKING FOR GENERATING EXPRESSIVE AVATARS simplified abstract

MULTI-MODAL THREE-DIMENSIONAL FACE MODELING AND TRACKING FOR GENERATING EXPRESSIVE AVATARS

Organization Name

microsoft technology licensing, llc

Inventor(s)

Harpreet Singh Sawhney of Kirkland WA (US)

Benjamin Eliot Lundell of Seattle WA (US)

Anshul Bhavesh Shah of Baltimore MD (US)

Calin Cristian of Iasi (RO)

Charles Thomas Hewitt of Cambridge (GB)

Tadas Baltrusaitis of Cambridge (GB)

Mladen Radojevic of Belgrade (RS)

Kosta Grujcic of Belgrade (RS)

Ivan Stojiljkovic of Belgrade (RS)

Paul Malcolm Mcilroy of Cambridge (GB)

John Ishola Olafenwa of London (GB)

Jouya Jadidian of Los Gatos CA (US)

Kenneth Mitchell Jakubzak of Lynnwood WA (US)

MULTI-MODAL THREE-DIMENSIONAL FACE MODELING AND TRACKING FOR GENERATING EXPRESSIVE AVATARS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240127522 titled 'MULTI-MODAL THREE-DIMENSIONAL FACE MODELING AND TRACKING FOR GENERATING EXPRESSIVE AVATARS

Simplified Explanation

The patent application relates to generating expressive avatars using multi-modal three-dimensional face modeling and tracking.

• Computer system with a processor and storage system
• Instructions stored in the storage system
• Processor receives initialization data describing initial state of facial model
• Processor receives multi-modal data signals
• Fitting process performed using initialization data and multi-modal data signals
• Set of parameters determined based on fitting process, describing updated state of facial model

Potential Applications

This technology could be applied in virtual reality, gaming, animation, and teleconferencing industries for creating realistic and expressive avatars.

Problems Solved

This technology solves the problem of creating detailed and expressive avatars in real-time applications, enhancing user experience and interaction.

Benefits

The benefits of this technology include improved realism, expressiveness, and customization of avatars, leading to more engaging and immersive user experiences.

Potential Commercial Applications

Potential commercial applications of this technology include virtual reality platforms, gaming companies, animation studios, and telecommunication companies looking to enhance their avatar creation capabilities.

Possible Prior Art

One possible prior art could be existing facial recognition and tracking technologies used in various applications such as security systems, augmented reality filters, and video conferencing software.

How does this technology compare to existing avatar creation methods?

This article does not provide a direct comparison to existing avatar creation methods, leaving the reader to wonder about the advantages and disadvantages of this technology in relation to current practices.

What are the potential limitations or challenges of implementing this technology?

The article does not address any potential limitations or challenges that may arise in implementing this technology, leaving room for speculation on the practicality and feasibility of its application.

Original Abstract Submitted

examples are disclosed that relate to generating expressive avatars using multi-modal three-dimensional face modeling and tracking. one example includes a computer system comprising a processor coupled to a storage system that stores instructions. upon execution by the processor, the instructions cause the processor to receive initialization data describing an initial state of a facial model. the instructions further cause the processor to receive a plurality of multi-modal data signals. the instructions further cause the processor to perform a fitting process using the initialization data and the plurality of multi-modal data signals. the instructions further cause the processor to determine a set of parameters based on the fitting process, wherein the determined set of parameters describes an updated state of the facial model.