Nvidia introduced DLSS 5 at GTC 2026, marking a major shift in graphics technology. Unlike earlier versions focused on upscaling and frame generation, DLSS 5 uses AI to generate complete pixels through neural rendering. CEO Jensen Huang called it a paradigm shift, as DLSS continues to power over 750 games globally.

Announced at Nvidia's GTC 2026 keynote on March 16, DLSS 5 is the most significant update to Nvidia's Deep Learning Super Sampling technology since it first launched in 2018. While previous versions of DLSS focused on boosting frame rates by generating pixels and frames, DLSS 5 takes an entirely different approach - one that Nvidia CEO Jensen Huang is calling nothing short of a paradigm shift for real-time graphics.

What DLSS actually is?

DLSS, or Deep Learning Super Sampling, is an AI-powered technology built into Nvidia's GeForce GPUs that helps games look and run better. Launched in 2018 as an AI technology to boost performance - first by upscaling resolution and then by generating entirely new frames - it has been integrated into over 750 games, becoming a gold standard for the industry. Earlier this year, DLSS 4.5 used AI to draw 23 out of every 24 pixels seen on screen. DLSS 5 is a step change beyond all of that.

DLSS 5 brings neural rendering in real time