DLSS 5 looks like a real-time generative AI filter for video games

"Nvidia announced DLSS 5 on Monday during its GTC conference, and based on early reactions, it's going to be a divisive update, with some reactions calling it "slop" that unacceptably alters artistic intent. Nvidia CEO Jensen Huang is calling this the "GPT moment for graphics - blending hand-crafted rendering with generative AI to deliver a dramatic leap in visual realism while preserving the control artists need for creative expression.""

"In games that support DLSS 5, the tools can immediately provide noticeable boosts to lighting and shadows, but unlike previous versions of upscaling that used machine learning to close the gap between high and low graphics settings, this version applies generative AI to rework the lighting and materials with details that feel newly added."

"The AI model is trained end to end to understand complex scene semantics such as characters, hair, fabric and translucent skin, along with environmental lighting conditions like front-lit, back-lit or overcast - all by analyzing a single frame. DLSS 5 then uses its deep understanding to generate visually precise images that handle complex elements."

Nvidia announced DLSS 5 at its GTC conference, introducing generative AI technology that modifies game lighting, shadows, and materials beyond traditional upscaling. Unlike previous versions that used machine learning to bridge graphics settings, DLSS 5 applies AI to rework visual elements with newly generated details. CEO Jensen Huang describes it as a "GPT moment for graphics," combining hand-crafted rendering with generative AI for enhanced visual realism. The technology analyzes scene semantics including characters, fabric, and environmental lighting conditions from single frames. Early reactions are mixed, with some praising improved realism in games like Resident Evil Requiem and Starfield, while others criticize the changes as "AI slop" that compromises artistic vision.

Read at The Verge