Internship] R&D Developer Assistant

Job Description

Fully simulating ocean dynamics in a real-time context is computationally too expensive to achieve for most interactive applications such video games. To overcome this, procedural ocean synthesis techniques that aim at reproducing wave behavior and surface appearance can be used. While existing methods like fast orientable aperiodic ocean synthesis using tiling and blending [1] offer some control (here on wave orientation), they are typically static and not responsive to dynamic changes such as terrain deformation, wind variations and user interactions. 

The goal of this internship is to investigate how neural embeddings can be used to learn a latent control space for ocean synthesis. These embeddings would be trained from offline simulation and stored as textures leveraging the fact that recent work on real-time neural materials [2] demonstrates how such latent spaces can be efficiently stored and accessed in a real-time context. Building on this, a secondary goal is to explore how these latent embeddings can also drive visual effects for rendering by integrating neural BRDF modeling [3] for water specific effects. 

The scope of this internship is research oriented. The student will be expected to survey the literature on ocean synthesis, latent space controllability, and neural rendering techniques. They will identify relevant methods and limitations in existing approaches, and implement small demonstrators to explore how these ideas can be adapted to real-time applications.

References 

1. Lutz N., Schoentgen A., and Gilet G. "Fast orientable aperiodic ocean synthesis using tiling and blending." ACM on Computer Graphics and Interactive Techniques (2024) 
2. Weinreich C., De Oliveira L., Houdard A., and Nader G. “Real‐Time Neural Materials using Block‐Compressed Features” Computer Graphics Forum (2024) 
3. Zeltner T. et al. "Real-time neural appearance models." ACM Transactions on Graphics (2024) 

Qualifications

• Master student in second year of a research-oriented master 
• Solid foundation in machine learning, linear algebra, and optimization. 
• Knowledge of computer graphics fundamentals (e.g., rendering pipelines, shading, or texture mapping). 
• Good communication skills in English, written and spoken.