"DLSS 5 fuses controllability of the of geometry and textures and everything about the game with generative AI. It's not post-processing, it's not post-processing at the frame level, it's generative control at the geometry level."
"Well, first of all, they're completely wrong. You can fine tune the generative AI to your artistic style. If you want cartoon, toon shader, made of glass, it's up to the developer."
"That's due at least in part to how demo videos show before and after comparisons that make characters' faces in games like Starfield and Hogwarts Legacy look like yassified stunt doubles, creating perception of the tech as a sort of slop filter that adds an uncanny layer of hyper-fidelity based on generic training models."
Nvidia introduced DLSS 5, a generative AI upscaling technology designed to enhance game visuals, but faced significant online backlash over concerns that it produces artificial-looking character faces and homogeneous results. CEO Jensen Huang responded to criticism by emphasizing that developers maintain complete control over the technology. He explained that DLSS 5 operates at the geometry and texture level, not as post-processing, allowing developers to fine-tune the generative AI to match their artistic vision. Huang cited support from major studios like Capcom and Bethesda, arguing the technology preserves artistic control while adding a new layer of visual fidelity. However, public perception remains skeptical, with many viewing the technology as applying generic AI enhancements rather than respecting original artistic intent.
Read at Kotaku
Unable to calculate read time
Collection
[
|
...
]