Internship R&D Developer Assistant - Real-Time Controllable Ocean Synthesis F - M - Nb H/F - 33

Ubisoft is a global leader in gaming with teams across the world creating original and memorable gaming experiences, from Assassin's Creed, RainbowSix to Just Dance and more. We believe diverse perspectives help both players and teams thrive. If you're passionate about innovation and pushing entertainment boundaries, join our journey and help us create the unknown!

Ubisoft Bordeaux

Founded in 2017 by a handful of Ubisoft experts, our studio now counts over 400 talents from 20 different nationalities. Our teams contribute to some of Ubisoft's biggest franchises: leading the production ofAssassin's Creed Miragein 2023, working onAssassin's Creed Shadowsand theClaws of Awajiexpansion, as well as onBeyond Good & Evil 2.

Beyond our AAA productions, we also drive technological innovation within the group through our expertise in the Anvil game engine and Ubisoft's Online Services. We have also established a dedicated R&D division, La Forge, which brings together Ubisoft engineers and academic researchers to collaborate on prototypes that support game development, particularly in the field of AI.

In 2024, we inaugurated our new offices in the Bastide-Niel eco-district, designed to foster the development of Ubisoft's best gaming experiences and technologies in an exceptional, accessible, and central environment.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
- Lutz N., Schoentgen A., and Gilet G. "Fast orientable aperiodic ocean synthesis using tiling and blending." ACM on Computer Graphics and Interactive Techniques (2024)
- Weinreich C., De Oliveira L., Houdard A., and Nader G. RealTime Neural Materials using BlockCompressed Features Computer Graphics Forum (2024)
- Zeltner T. et al. "Real-time neural appearance models." ACM Transactions on Graphics (2024)