NVIDIA Real-Time Graphics Research

submited by

Style Pass

2024-10-30 18:30:06

Welcome to the team page for NVIDIA’s real-time graphics research group! We aim to define the future of 3D scene creation, manipulation, and rendering with cutting-edge research covering real-time rendering; differentiable rendering; machine learning; light transport; material and shape generation, modeling, and acquisition; image metrics; graphics systems and programming models; and ways all of these interact.

Our mandate is to envision real-time graphics in 5, 10, or 20 years. We also productize successful research in various ways, including impacting GPU architectures, NVIDIA products (e.g., Omniverse and GeForce SDKs), graphics APIs, and direct sharing of knowledge with developers via papers, talks, courses, and blogs.

Internships on our team usually start by interested graduate students directly contacting potential research mentors on our team, either via e-mail, social media, or in person at a conference. Most interns join us during the summer, but we welcome interns year round.

Recent advancements in spatiotemporal reservoir resampling (ReSTIR) leverage sample reuse from neighbors to efficiently evaluate the path integral. Like rasterization, ReSTIR methods implicitly assume a pinhole camera and evaluate the light arriving …