NVIDIA DLSS technique gets analyzed (video)

NVIDIA's GeForce RTX series has arrived, we now know how it performs in current games but the jury is still out on RTX and DLSS. EuroGamer just published a detailed analysis of the latter. DLSS stands for Deep Learning Super Sampling, it's a new anti-aliasing technique that uses AI to speed up performance by rendering images at a lower resolution and then using a pre-trained deep learning algorithm to produce higher resolution imagery.

The potential performance gains cited by NVIDIA sound impressive, but does it really work? EuroGamer's DigitalFoundry tried DLSS in a tech demo of Final Fantasy 15 and notes that in some cases, DLSS provides better image quality results than TAA. If you check out the closeups though, TAA often has much sharper image quality.

But has Nvidia truly managed to equal native quality? For the most part, it passes muster and inaccuracies and detail issues are only truly noticeable when conducting direct side-by-side comparisons - but we did note that in the demo's climactic zoom-out to show the high detail city, the lower base resolution does have an impact on the quality of the final image. Is it likely to distract a user playing the game and not conducting detailed side-by-side comparisons? Highly unlikely.

At the moment, it's still too early to tell whether DLSS is a wonder solution. The demos look impressive, but so far journalists and gamers haven't had a chance to actually play a game with DLSS yet. It will also be interesting to see how DLSS 2X performs, that technique promises to deliver higher image quality while keeping the framerate the same.