Intern, Hair Compression for Avatar Representation

About InterDigital

InterDigital is a global research and development company focused primarily on wireless, video, artificial intelligence (“AI”), and related technologies. We design and develop foundational technologies that enable connected, immersive experiences in a broad range of communications and entertainment products and services. We license our innovations worldwide to companies providing such products and services, including makers of wireless communications devices, consumer electronics, IoT devices, cars and other motor vehicles, and providers of cloud-based services such as video streaming. As a leader in wireless technology, our engineers have designed and developed a wide range of innovations that are used in wireless products and networks, from the earliest digital cellular systems to 5G and today’s most advanced Wi-Fi technologies. We are also a leader in video processing and video encoding/decoding technology, with a significant AI research effort that intersects with both wireless and video technologies. Founded in 1972, InterDigital is listed on Nasdaq.

InterDigital is a registered trademark of InterDigital, Inc.

For more information, visit:

Summary

The InterDigital Immersive Video Lab is dedicated to advancing avatar-based communication. In this context, accurate acquisition, modeling, and transmission of avatar hair models are critical to achieving photorealistic avatar rendering. Modeling hair remains a significant challenge due to its complex geometry of thin, intertwined strands.

State-of-the-art hairstyle models represent hair as a collection of 3D strand curves anchored on the surface of the 3D head mesh of an avatar. The memory footprint of such models can be quite large, creating a bottleneck in the avatar transmission pipeline.

The purpose of the internship will be to explore compression approaches for reducing the data volume of hair models. Both AI-based dimensionality reduction techniques and data analysis methods such as tensor decomposition could be considered. A large dataset of synthetic 3D hair models will be made available for this purpose.

Responsibilities

State-of-art on human face and hair representation models.

Development of a baseline compression technique based on Principal Component Analysis.

Implementation and evaluation of compression techniques on hair data

Qualifications

M.Sc. or Grande Ecole with majors in data science, deep learning, applied mathematics and/or computer graphics.

Fluency in English is essential.

Experience in Python and Git is required.

Familiarity with computer graphics platforms such as Blender would be a plus.

Keywords: avatar-based communication, digital human face and hair models, data compression

Expected Outcomes: patents, publications and software modules.

Location: Rennes, France

InterDigital is an equal employment opportunity employer. InterDigital will not engage in or tolerate unlawful discrimination with regard to any employment decision, policy or practice based on a person’s sex, gender, pregnancy (including childbirth, breastfeeding and related medical conditions), age, race, color, religion, creed, national origin, ancestry, citizenship, military status, veteran status, mental or physical disability, medical condition, genetic information, sexual orientation, gender identity or expression, or any other factor protected by applicable federal, state or local law. This policy applies to all terms and conditions of employment, including, but not limited to, recruiting, hiring, compensation, benefits, training, assignments, evaluations, coaching, promotion, discipline, discharge and layoff.

REQ25-1032