Organisation/Company: CNRS
Department: Laboratoire des sciences de l'Ingénieur, de l'Informatique et de l'Imagerie
Research Field: Engineering, Computer Science, Mathematics
Researcher Profile: Recognised Researcher (R2)
Country: France
Application Deadline: 28 Nov 2024 - 23:59 (UTC)
Type of Contract: Temporary
Job Status: Full-time
Hours Per Week: 35
Offer Starting Date: 1 Apr 2025
Is the job funded through the EU Research Framework Programme? Not funded by a EU programme
Is the Job related to staff position within a Research Infrastructure? No
Offer Description In the framework of a binational, tri-institutional project titled HuMoCar: Realistic Human Models for Care Robots for Aged People (October 2021 - October 2025), our objective is to improve the robustness of vision and artificial intelligence systems against large variations and occlusion. This project also aims to facilitate the management of specific interactions by developing a realistic, physics-compliant 4D human model. Our specific goal is to develop a predictive/generative model for clothed humans and dynamic garments, using deep learning on annotated datasets. Several downstream tasks will be defined and developed, involving various conditional generations. Geometric deep learning models will be deployed to process 3D surface data, based on a homogeneous representation of garment surface data. The project will take place within the MLMS research team (Machine Learning, Modeling & Simulation, https://mlms.icube.unistra.fr/ ), located on the laboratory's hospital site.
Responsibilities Research and development on the aforementioned topic: Predictive/generative modeling of clothed humans and garments. This involves predicting the shape and physical behavior of clothed individuals, considering the laws of physics and 3D simulation.
Technical management and collaboration with other researchers (PhD students, engineers, post-docs, and permanent researchers) involved in the project: This involves organizing the team's work, assigning responsibilities, and ensuring the technical coherence of the project.
Potential supervision of Master's students.
Qualifications PhD in Computer Science (2022 or later), with at least one very good publication.
Solid knowledge and experience in deep learning.
Excellent programming skills, expertise in designing efficient algorithms, and proficiency in academic writing.
English level C or higher.
Team spirit.
#J-18808-Ljbffr