Internship

Intern, Video Lab - Grooming Generation and Segmentation

Rennes (France)
Student / Recent Graduate
InterDigital
Sciences, Engineering & R&D

The Job

Grooming Data Generation and Segmentation About InterDigital InterDigital develops fundamental wireless technologies that are at the core of mobile devices, networks, and services worldwide. We solve many of the industry's most critical and complex technical challenges, providing solutions for more efficient broadband networks and a richer multimedia experience years ahead of market deployment. InterDigital has strategic relationships with many of the world's leading wireless companies.  Founded in 1972, InterDigital is listed on NASDAQ and is included in the S&P SmallCap 600 Index.  For more information please visit interdigital.com Description : Interdigital Immersive Video lab is working on semantic-based technology for videoconferences. In this context digital human data is key to estimate semantic features correctly and precisely such as facial expressions, lighting conditions (e.g. light positions or specular reflections) and background. The MetaVideo group has worked on hair modeling, encoding and segmentation for a couple of years in relation with postproduction studios and has built a large VFX haircut database. The group would like to explore the possibility to leverage its dataset to coding hair semantic information. The goal of the internship will be to: Generate synthetic data of hair dynamic video data on Unreal Engine Implement a solution to segment hair on human front monocular video Propose a solution to a fitting problem between segmented hair and haircuts database The intern will be included in the Video lab in Rennes, France within the Interactive Media project. All the 3D assets (haircuts, head mesh) are already available. Professional tools such as Autodesk Maya or SideFX Houdini will also be provided in complement to a geometry processing framework. References : [1] Erroll Wood, Tadas Baltrušaitis, Charlie Hewitt, Sebastian Dziadzio, Thomas J. Cashman, Jamie Shotton ; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 3681-3691 Skills : computer graphics, 3D modeling, rendering, Maya/Houdini/Blender Keywords : computer graphics, synthetic data, machine learning 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.
See full jobBack to overview
InterDigital