Since AMD announced the FidelityFX Super Resolution (FSR) technology at Computex this year, it has aroused a wide range of discussions between professionals and ordinary players, proving that this technology is highly anticipated. Microsoft has already integrated FidelityFX Super Resolution into the Xbox Game Development Kit (GDK), supporting Windows, Xbox Series S/X, Xbox One(X). Competitor Sony has never announced that FSR will be included in the game development kit, but it already supports games on the PlayStation 5 platform.
AMD has also fulfilled its open-source promise when it was launched, putting the source code, development documents, and examples of FidelityFX Super Resolution on the AMD GPUOpen website. This makes the folk technology enthusiasts quite active in the development, such as applying FidelityFX Super Resolution to almost all Vulkan games (including dxvk and vkd3d-proton) under the Linux environment or adding it to SteamVR, allow VR games to take advantage of AMD’s technology.
Recently, AMD Engineering Director Nick Thibieroz said in an interview with Eurogamer
that developers’ acceptance and adoption rate of FidelityFX Super Resolution needn’t be said much, and the results are gratifying. FSR 1.0 is the result of AMD’s extensive research, and multiple teams use various basic upgrade technologies to explore different solutions. ” Given the goals we had set out, we chose to release FSR 1.0 as we know it would appeal to a large number of developers and gamers who want to be able to enjoy high-quality gaming at faster frame rates on multiple platforms, without being limited by proprietary hardware.”
In addition, in the interview, Nick Thibieroz answered why FidelityFX Super Resolution does not use machine learning (ML) as NVIDIA does. “If we’re being objective about ML and upscaling algorithms, I think the first iteration of NVIDIA DLSS is a good illustration of what I’m talking about here. The mere presence of ML in a solution does not imply you are going to get great results. ML clearly shows promise, and AMD is heavily investing in ML R&D on a number of fronts, but just because an algorithm uses ML does not mean it’s the overall best solution given a set of goals.“