NVIDIA DLSS version 2.3 technology has been around for over a month now, and despite this, the company has not made any official announcements to date. However, the company released a new video about it (which for some reason was only posted for a few hours and now they’ve taken it down) where they didn’t hesitate to attack the. FSR technology of the competition, claiming that DLSS 2.3 is better than the spatial scale used by AMD.
It was Bryan Catanzaro (VP of Applied Deep Learning Research at NVIDIA) who explained in this retired video how existing spatial scaling technologies, such as AMD Fidelity FX Super Resolution (FSR), compare. The NVIDIA employee pointed out that DLSS has been in development for many years, and has been receiving updates for 3 years, while competing technologies have not.
Is NVIDIA DLSS 2.3 better than AMD FSR?
Any hardware enthusiast will remember the fiasco that resulted in the first version of NVIDIA DLSS technology, and most experts agree it was too early. However, NVIDIA has learned its lesson very well and DLSS 2.0 has indeed revolutionized game resolution scaling with the introduction of AI Image Reconstruction which has dramatically improved image quality.
At the time of DLSS 2.0 release, NVIDIA made it clear that it was paying close attention to feedback from developers and the community regarding the issues with the first version, and that it has since improved its technology. With DLSS version 2.3, smarter use of motion vectors is introduced in games, which improves detail and greatly reduces the effect. ghost and the wavering on moving objects, one of the weakest points of technology.
In the video released and subsequently deleted by NVIDIA, we could see how the company was focusing on a comparison between DLSS and conventional spatial scaling technology that has been around for years. The technology, according to Catanzaro, has even been implemented in televisions, and in fact, he adds that GeForce controllers have long offered their own way of performing spatial scaling.
The video presents a comparison between DLSS technology in different quality and space improvement modes in games such as Back 4 Blood, Necromunda Hired Gun or Chernobylite. It’s also curious that NVIDIA doesn’t mention AMD’s FSR technology in any of the cases, treating it like any spatial enhancement technology even though, as is evident, they compare DLSS and FSR in all games.
It’s such a shame that NVIDIA removed the video they posted and we couldn’t show it to you here, and it’s also strange that the company did so without giving any explanation … we can’t to know if maybe it was posted early by mistake, yes it is because the video had inaccurate data, or if they had some problem, especially for the FSR issue.
By answering the question of the statement, we cannot say whether DLSS 2.3 is really better than AMD FSR, but what is clear is that in all the comparisons that have been made to date it has been possible to see that both technologies have gained a place and they are here to stay, as the performance improvements that both provide are more than remarkable.
We are faced with two technologies clashing in the eternal AMD vs NVIDIA fight, but we are forced to mention here Intelligence and its technology XeSS, which we cannot lose sight of because it will come into play against the two technological giants. On the flip side, we also have to mention the fact that there will come a time when AMD will update FSR to, like DLSS, be AI-based, which will again set things very hot between the two companies.
