*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

Moyens / Méthodes / Logiciels

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., Diplôme préparé

Bac+5 - Master 2

Durée du contrat (en mois)

6 mois

Entité de rattachement

Le CEA est un acteur majeur de la recherche, au service des citoyens, de l’économie et de l’Etat.

Il apporte des solutions concrètes à leurs besoins dans quatre domaines principaux : transition énergétique, transition numérique, technologies pour la médecine du futur, défense et sécurité sur un socle de recherche fondamentale. Le CEA s’engage depuis plus de 75 ans au service de la souveraineté scientifique, technologique et industrielle de la France et de l’Europe pour un présent et un avenir mieux maîtrisés et plus sûrs.

Implanté au cœur des territoires équipés de très grandes infrastructures de recherche, le CEA dispose d’un large éventail de partenaires académiques et industriels en France, en Europe et à l’international.

Les 20 000 collaboratrices et collaborateurs du CEA partagent trois valeurs fondamentales, 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.