Nvidia announced DLSS 5 at GTC on March 16, 2026, calling it the most significant breakthrough in computer graphics since real-time ray tracing debuted in 2018.
DLSS 5 introduces a real-time neural rendering model that takes a game's color and motion vectors for each frame as input, then uses AI to infuse the scene with photoreal lighting and materials anchored to the source 3D content. The AI model runs in real time at up to 4K resolution for smooth, interactive gameplay.
The neural model is trained end-to-end to understand complex scene semantics — characters, hair, fabric, translucent skin — along with environmental lighting conditions, producing frame-to-frame visual consistency.
Major publishers have signed on, including Bethesda, CAPCOM, Hotta Studio, NetEase, NCSOFT, S-GAME, Tencent, Ubisoft, and Warner Bros. Games. Players will be able to toggle the feature on or off based on preference.
However, reception has been sharply divided. The official livestream accumulated over one million views but showed roughly 82,000 negative reactions against only 16% positive feedback. Critics argue DLSS 5 drastically alters the original art direction of supported games, with some calling it a 'garbage AI filter' that overwrites developers' artistic vision.
DLSS 5 is expected to arrive in fall 2026.