Sony PlayStation's chief architect has confirmed the use of Machine Learning to produce smoother visuals, aiming to make gaming more enjoyable, with the earliest implementation likely on the PS5 Pro.
Mark Cerny, the lead architect behind the PlayStation 5 and PS5 Pro, told Digital Foundry that Sony is developing frame generation technology using Machine Learning for future PlayStation platforms. This technology uses AI to create new frames inserted between actually rendered frames to improve smoothness. It builds upon the existing PSSR (PlayStation Spectral Super Resolution) technology currently used for upscaling on the PS5 Pro. This approach is similar to PC technologies that enhance image continuity, although technically it may introduce a slight increase in latency.
An interesting point is that it remains unclear whether this Machine Learning-based frame enhancement will launch on the PS5 Pro or be reserved as a key feature of the PlayStation 6.
The release of the PS6 may be delayed due to ongoing RAM supply chain issues, pushing its launch beyond 2027. Therefore, the most likely scenario is that this AI frame generation technology will debut alongside new hardware in the future.
Notably, if Sony can apply AI in this way similar to Nvidia's DLSS, it would produce visuals that are more accurate and visually pleasing. Currently, AMD's FSR3 frame generation technology is used in some PS5 games, but unlike DLSS, FSR3 does not use Machine Learning; instead, it relies on traditional frame interpolation techniques.
.. Experts in the gaming industry believe that AI-based frame generation for smoother visuals is not a solution for games with very low frame rates. The system requires a stable baseline frame rate to provide enough data for the AI to create new frames accurately without distortion.
Source:The Verge