Image reconstruction technologies are here to stay. The appetite of the industry and video game enthusiasts to combine high resolutions, a high-quality graphic finish and a high rate of images per second is on the table. However, even the most advanced graphics hardware often doesn’t is able to deal simultaneously with these three requirements.
The purpose of image reconstruction technologies such as DLSS (Deep Learning Super Sampling) from NVIDIA or FSR (FidelityFX Super Resolution) from AMD, among other options, is precisely unlock graphics hardware part of the load imposed by this usage scenario. What they are after, in short, is to make high resolutions and higher quality graphics compatible with a very high sustained rate of images per second.
However, although they aspire to achieve the same goal, the philosophy of the technologies proposed by NVIDIA and AMD it’s very different. Broadly speaking, while DLSS uses real-time analysis of the frames of our games using deep learning algorithms, FSR uses a spatial scaling procedure that does not require any prior learning, although it must be explicitly implemented in games.
The image quality offered by the latest versions of NVIDIA technology is higher than that provided by AMD in the same scenario of use, but we must not overlook that DLSS 2.0 represented a breakthrough very important compared to the original version of this technology. And it is possible that FSR 2.0, which has just been officially announced by AMD, will do the same.
FidelityFX Super Resolution 2.0 Bets on Time Scaling
AMD has changed its strategy. And it is that instead of continuing to refine the spatial scaling used in the original version of the FSR technology, it has opted for redesign from scratch its image reconstruction algorithm with the purpose of “delivering an image quality similar to, or even superior to, the native image, but drastically increasing the rate of images per second in those games that support it”.
This is what AMD is telling us, and while it looks good, we won’t know if FSR 2.0 really lives up to the hype it’s generating until we get a chance to test it. In any case, this is not the only thing that this company has released today. It has also given us some interesting clues about operation of what is currently its most advanced image reconstruction technology.
The temporal scaling procedure implemented in FSR 2.0 analyzes each frame’s color, depth, and motion vectors handled by the logic elements involved in the render pipeline, as well as descriptive information from previous frames, to create a new image that, in theory, achieves retrieve a very high level of detail. And, at the same time, it minimizes the jagged edges of objects displayed on the screen.
AMD ensures that the temporal scaling of FSR 2.0 offers us an image quality significantly higher than the spatial scaling used by FSR 1.0
AMD ensures that FSR 2.0 offers us an image quality noticeably higher than the spatial scaling used by FSR 1.0. And possibly it will, but again we want to remember that it is reasonable not to take anything for granted until we can analyze this technology. In the following composition we can see a comparison of image quality made by AMD that aims to show us the difference in quality that exists between the image at native resolution, FSR 1.0 and FSR 2.0. It will be very interesting to face this latest revision to NVIDIA’s DLSS 2.x technology.
Like FSR 1.0, the new iteration of this technology is an open source solution, so a priori it can be used by other hardware manufacturers. AMD has confirmed that FSR 2.0 will be available during the second trimester this year, so there’s a good chance we won’t have to wait long to put it to the test. Let’s cross our fingers for it to be so. One last note: ‘Deathloop’ will be one of the first games to implement it.
More information | amd
George is Digismak’s reported cum editor with 13 years of experience in Journalism