Object detection by parametrization using elementary 3D shapes H/F

General information

Organisation

The French Alternative Energies and Atomic Energy Commission (CEA) is a key player in research, development and innovation in four main areas :

• defence and security,

• nuclear energy (fission and fusion),

• technological research for industry,

• fundamental research in the physical sciences and life sciences.

Drawing on its widely acknowledged expertise, and thanks to its 16000 technicians, engineers, researchers and staff, the CEA actively participates in collaborative projects with a large number of academic and industrial partners.

The CEA is established in ten centers spread throughout France

  

Reference

2024-33197  

Description de l’unité

Based in Saclay (Essonne), the LIST is one of the two institutes of CEA Tech, the Technological Research Division of the CEA. Dedicated to intelligent digital systems, its mission is to carry out technological developments of excellence on behalf of industrial partners, in order to create value.
Within the LIST, the Laboratory of Vision and Learning for Scene Analysis (LVA) conducts its research in the field of computer vision and artificial intelligence for the perception of intelligent and autonomous systems. The laboratory’s research themes include visual recognition, behavior and activity analysis, large-scale automatic annotation, and perception and decision models.

Position description

Category

Mathematics, information, scientific, software

Contract

Internship

Job title

Object detection by parametrization using elementary 3D shapes H/F

Subject

Developing an object detector in images that can be parametrized with a 3D prompt made of an orchestration of elementary shapes. This detector will rely on deep learning technologies.

Contract duration (months)

6

Job description

Missions

Computer vision is currently at a turning point, with the convergence of visual, audio and, above all, textual modalities. This convergence is making it increasingly possible to benefit from or pool the knowledge generated by these different modalities. This knowledge is also becoming ‘fundamental’, meaning that it transgresses the ontologies of databases and seeks to move towards a holistic representation of their field of expertise. To interrogate these fundamental models, it is necessary to use a prompt, which is often text-based. This is the case for object detection with Open Vocabulary detection. However, it is not always simple or practical to describe an object in text only. Describing it using an image, a sketch or a CAD model may be more relevant in certain contexts, particularly in industry.

As an intern at the CEA’s Vision and Learning Laboratory, you will help develop innovative technologies for using 3D CAD models as prompts for Open Vocabulary object detection, with a particular focus on object and model shape. You will be ask to :
• Develop zero-shot object detector algorithms using breakthrough neural network technology
• Analyze and summarize existing algorithms then propose realistic development plans.
• Identify and make effective use of the computing resources needed
• Keep environmental constraints in mind and integrate the development of solutions into a responsible approach.
• Collaborate and participate in the exchange of knowledge within the laboratory in order to cultivate the laboratory’s scientific
excellence.
• Promote the work carried out through communication media, demonstrators and/or scientific publications.

Job-related benefits

Join CEA List and LVA as an intern to:
• Work in one of the most innovative research organizations in the world, addressing societal challenges to build the world of tomorrow
• Discover a rich ecosystem: privileged connections between the industrial and academic sectors
• Conduct research autonomously and creatively: encouragement to valorize results (scientific articles, patents, open-source codes…)
• Join a young and dynamic team
• Benefit from an internal computing infrastructure with more than 300 state-of-the-art GPUs
• Receive a stipend between €1300 and €1400 per month
• Have the opportunity to continue with a PhD or as a research engineer after the internship
• Have the possibility of remote work, receive a 75% reimbursement on public transportation costs, and benefit from the “mobili-jeune” aid to reduce rent costs…

In line with CEA’s commitment to integrating people with disabilities, this job is open to all.

More details on https://kalisteo.cea.fr/index.php/apply-for-a-job/

Methods / Means

3D shape representation, 3D shape retrieval, 3D shape clustering, deep learning

Applicant Profile

• Students in their 5th year of studies (M2)
• Computer vision skills
• Machine learning skills (deep learning, LLM, VLM, generative AI…)
• Python proficiency in a deep learning framework (especially PyTorch or TensorFlow)

Position location

Site

Saclay

Job location

France, Ile-de-France, Essonne (91)

Location

Palaiseau

Candidate criteria

Languages

French (Fluent)

Prepared diploma

Bac+5 – Master 2

Recommended training

Ecole d’ingénieur ou Master 2 recherche en informatique et IA

PhD opportunity

Oui

Requester

Position start date

03/02/2025