DLSS 3.5 Is More Beautiful Than Native Rendering, Frame Generation Produces “Much Realer” Frames Than Traditional Graphics Frames: NVIDIA

The FPS Review may receive a commission if you purchase something after clicking a link in this article.

Image: NVIDIA

Native rendering will always be the best choice for players who want maximum fidelity out of their games, right? Not quite, according to Bryan Catanzaro, vice president of Applied Deep Learning Research at NVIDIA, who told Digital Foundry in a new Cyberpunk 2077: Phantom Liberty AI Visuals Roundtable video published yesterday that DLSS 3.5, a new version of the technology that introduces Ray Reconstruction for improved ray tracing visuals, actually enables even better visuals than what native rendering can provide thanks to AI. Catanzaro, who can also be found in NVIDIA’s DLSS 3.5 videos, also addressed some of the controversy behind Frame Generation’s “fake frames,” claiming that they are “much realer” than traditional graphics frames.

…you know, I think DLSS 3.5 actually makes Cyberpunk even more beautiful than native rendering…that’s my belief…playing cyberpunk using DLSS is more beautiful than native, and the reason for that, again, is because you know the AI is actually able to make smarter decisions about how to render the scene than what we knew how to do without AI, and I think that’s going to continue to develop.

…I would say that Cyberpunk frames using DLSS, including Frame Generation, are much realer than traditional graphics frames. You know, if you think about all of the graphics tricks, like all the different kinds of occlusion and shadows, and fake reflections, screen space effects, and like, you know, raster in general, is just a bag of fakeness, right?

Join the discussion in our forums...

Tsing Mui
News poster at The FPS Review.

Recent News