Internship 3D Reconstruction in the Dark: Radiance Fields for Unlit Environments-Saclay-H/F

CEA; Saclay; On-site; EUR 10,000 - 17,000; Part time

Job summary

CEA List à Saclay propose un stage en Reconstruction 3D dans l’obscurité, utilisant des champs de radiance et l’intégration d’un système d’éclairage mobile pour des environnements non éclairés. Vous travaillerez au sein d’un laboratoire de pointe, avec accès à des ressources avancées et la perspective d’une publication.

Le candidat doit être en fin de cycle Master 2 ou école d’ingénieurs, maîtriser Python et PyTorch, et démontrer des compétences fortes en vision par ordinateur et apprentissage

Qualifications

• Actuellement en dernière année de Master (M2) ou école d'ingénieurs (y compris année sabbatique).
• Solides compétences en vision par ordinateur et apprentissage automatique, notamment.
• Excellente maîtrise de Python avec expérience d’un framework deep learning, préférence pour PyTorch.

Responsibilities

• Revue de l'état de l'art: analyser les méthodes de reconstruction 3D (NeRF, etc.).
• Prototypage: modéliser la source lumineuse dans le pipeline d'inverse rendering.
• Expérimentation: tester le système en scenarios réels ou simulés.
• Optimisation: améliorer robustesse et précision dans des environnements variés.
• Validation: comparer avec méthodes classiques et évaluer les gains.

Skills

Computer vision

Machine learning

Python

PyTorch

Education

Master 2

École d'ingénieurs

Tools

PyTorch

Job description

Internship 3D Reconstruction in the Dark: Radiance Fields for Unlit Environments-Saclay-H/F

Contrat

Stage

Internship 3D Reconstruction in the Dark: Radiance Fields for Unlit Environments-Saclay-H/F

3D reconstruction from images is a rapidly evolving field with major applications in robotics, augmented reality, archaeology, and industrial inspection. Modern methods, such as Neural Fields (NeRF, Instant NGP) and Gaussian Splatting, enable the creation of highly detailed and realistic 3D scenes. However, these approaches often assume well-lit and static environments, which limits their applicability in real-world scenarios where lighting is absent or variable. This internship proposes exploring an innovative approach: integrating a mobile embedded lighting system (e.g., a light source mounted on a robot) to enable 3D reconstruction in unlit or hard-to-access environments.

As an intern at the CEA, you will have the opportunity to work within a world-renowned research environment. Our teams consist of passionate and dedicated experts, providing an ideal setting for learning and collaboration. You will have access to state-of-the-art equipment and top-tier research resources to carry out your assignments. The work conducted may potentially lead to a scientific publication.

What do we expect from you?

The intern will be responsible for:

• State of the Art Review: Analyzing existing 3D reconstruction methods (NeRF, Gaussian Splatting) and their limitations in unlit environments.
• Prototyping: Implementing a solution that model the light source in the inverse rendering reconstruction pipeline.
• Experimentation: Testing the system in real or simulated scenarios, with different light configurations.
• Optimization: Improving robustness and the reconstruction accuracy (large environment, reflective sufaces)
• Validation: Comparing results with classical methods (with fixed lighting) and evaluating improvements in quality and robustness.

#Cea-List

python

• Currently enrolled in your final year of a Master's program (M2) or an Engineering School (including gap year students).
• Strong skills in computer vision and machine learning, particularly.
• High proficiency in Python alongside experience using a deep learning framework, with a strong preference for PyTorch.

Site

Saclay

Saclay

Bac+5 - Master 2

Référence

2026-42017

The CEA's List Institute is tasked with a mission of innovation and technology transfer for the benefit of the industrial sector. To achieve this, it draws upon its scientific expertise across a wide range of high-tech fields, including artificial intelligence, software design, simulation, cybersecurity, and quantum computing. Within the Institute—specifically within the Department of Ambient Intelligence and Interactive Systems (DIASI)—the Vision for Modeling and Localization Laboratory (LVML) conducts research in computer vision and artificial intelligence, focusing on perception for intelligent and autonomous systems. The laboratory's research themes include localization, 3D semantic reconstruction and modeling, the segmentation and characterization of objects and materials, and vision systems for robotics.