In the past few years, advancements in real-time rendering in Unreal Engine have gotten us many steps closer to path-traced quality. Come see how individual technologies available today, such as Lumen, Direct Illumination, Shader Execution Reordering, and Nanite, help us achieve scenes without limits. We'll also discuss next steps, looking ahead to a future where true real-time path tracing becomes possible.

While the horsepower of modern GPUs is booming, physically based real-time hair rendering is still far from being solved. While card-based hair used to be the most common modeling technique in games, strand-based hair is being used more and more frequently. However, drawing hair as millions of thin triangle strips with rasterization causes overdraw issues, putting a huge burden on GPUs. Considering the climbing ray-tracing performance of NVIDIA GPUs, it's worth exploring whether real-time ray-traced rendering can be a better choice than rasterization. We'll describe several attempts at using NVIDIA RTX to render hair strands with better efficiency and quality. There are three main aspects included: (1) efficient and accurate ray-strand intersection in DXR; (2) hybrid multiple scattering solutions and (3) strands-targeted de-noising.

The use of deep learning models for real-time graphics and offline creative industries has skyrocketed in the last year. In this session, we explore innovations from NVIDIA and its partners using generative models, large language models (LLMs) and multi-modal models. We also delve into new use-cases and growth areas for gamers, developers and content creators that are opening with these exciting new advancements.