NVIDIA DLSS 5 AI Upscaling Technology Announced for Games, Users Call It an "AI Slop Filter"

NVIDIA DLSS 5 has been announced as an AI rendering and upscaling technology but players seem to be disappointed with how it's working.

NVIDIA DLSS 5 AI rendering technology has been announced by the company. The technology "introduces a real-time neural rendering model that infuses pixels with photoreal lighting and materials," making the game look more photorealistic and lifelike. However, the demo videos shared by Nvidia seem to have disappointed fans with them calling the technology an "AI Slop filter."

NVIDIA DLSS 5 is being described as "the company's most significant breakthrough in computer graphics since the debut of real-time ray tracing in 2018." DLSS 5 introduces a real-time neural rendering model that infuses pixels with photoreal lighting and materials. "Bridging the divide between rendering and reality, DLSS 5 empowers game developers to deliver a new level of photoreal computer graphics previously only achieved in Hollywood visual effects," said NVIDIA.

Explaining how the technology works, the company said that DLSS 5 takes a game's colour and motion vectors for each frame as input, and uses an AI model to infuse the scene with photoreal lighting and materials that are anchored to source 3D content and consistent from frame to frame. Furthermore, DLSS 5 runs in real time at up to 4K Resolution for "smooth, interactive gameplay."

The company has trained the AI model 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 analysing a single frame. "DLSS 5 then uses its deep understanding to generate visually precise images that handle complex elements such as subsurface scattering on skin, the delicate sheen of fabric and light-material interactions on hair, all while retaining the structure and semantics of the original scene."

Also Read: NVIDIA G-SYNC Support for Samsung 2026 OLED TVs and Monitors Announced

NVIDIA DLSS 5 provides game developers with detailed controls for intensity, colour grading and masking, so artists can determine where and how enhancements are applied to maintain each game's unique aesthetic. NVIDIA adds that integration remains seamless, using the same NVIDIA Streamline framework used by existing DLSS and NVIDIA Reflex technologies.

Starting this fall, DLSS 5 will be supported by the industry's known publishers and game developers, including Bethesda, CAPCOM, Hotta Studio, NetEase, NCSOFT, S-GAME, Tencent, Ubisoft and Warner Bros. Games.

NVIDIA's DLSS 5

with a demo video showcasing the technology's capabilities, which has garnered over 46 million views and more than 20,000 comments at the time of writing, is filled with users complaining that the upscaled version of the game looks poor and undermines the art of 3D design. Many claim the technology replaces developer-created character faces with entirely new AI-generated ones.

This looks horrifically bad, nobody wants an AI slop filter on top of their games

It's just a realtime ai filter that slaps the faces of 3d artists

Like what's the point? Artists spend hours perfecting a model for you to come and replace it with AI Faces? I seriously hate this so much.

LOL. We've reached the point of diminishing returns in game visuals where companies have convinced themselves that some freaky AI filter that slaps an artistic direction in the face is progress worth sharing.

This is the AI slop people have been wanting to stay out of video games, but people are giving this a free pass (even if it looks horrible) because it has the Nvidia DLSS branding on it.