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.
We have over two dozen researchers and engineers located across Europe and North America.
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.
August 2024 - Our team presented numerous papers presented at SIGGRAPH 2024:
December 2023 - We had 4 papers presented in December at SIGGRAPH Asia 2023, including:
ACM Transactions on Graphics (SIGGRAPH), 2024
ACM Transactions on Graphics (SIGGRAPH), 2024
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 …
ACM Transactions on Graphics (ToG), 2024
ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D), 2024
🏆 Best Paper
2D texture maps and 3D voxel arrays are widely used to add rich detail to the surfaces and volumes of rendered scenes, and filtered texture lookups are integral to producing high-quality imagery. We show that applying the texture filter after …
PhD dissertation from Centre for Mathematical Sciences, Lund University, 2024
Rendered imagery is presented to us daily. Special effects in movies, video games, scientific visualizations, and marketing catalogs all often rely on images generated through computer graphics. However, with all the possibilities that rendering …
ACM Transactions on Graphics (ToG), 2024
ACM Transactions on Applied Perception (TAP), 2024
Edge detection is an important process in human visual processing. However, as far as we know, few attempts have been made to map the temporal edge detection filters in human vision. To that end, we devised a user study and collected data from which …
ACM Transactions on Graphics (SIGGRAPH Asia), 2023
ACM Transactions on Graphics (SIGGRAPH Asia), 2023
SIGGRAPH Asia (Conference Track), 2023
Recent work on generalized resampled importance sampling (GRIS) enables importance-sampled Monte Carlo integration with random variable weights replacing the usual division by probability density. This enables very flexible spatiotemporal sample …