AMD has now made the source code for FSR 2.2 publicly available, which enables all game developers to use this data to integrate the technology into their own software.
A useful chart has been provided by AMD that lists the alterations made and how they affect the overall image quality. One of the updates includes the enhancement of high dynamic range (HDR), resulting in fewer visible ‘fizzing’ artifacts and an improvement in temporal stability, which means less flickering for the user.
A new API debugger has been added as a new feature, aimed at simplifying the integration process for game developers who use FSR 2.2. However, the transition from FSR 2.0 to the latest versions is already easier than transitioning from the first version of FSR.
According to AMD’s recommendation, developers should rebuild all integrations instead of just swapping the library files. Furthermore, AMD reminds developers that there have been changes to the Reactive Mask and Transparency & Composition Mask texture upscaling in FSR 2.2, which may require adjustments.
AMD has confirmed that over 110 games are set to incorporate AMD FSR 2, with the total number of titles implementing FSR 1 surpassing 250.AMD has also confirmed that the FSR 2.2 update will soon be available as a plugin for the Unreal Engine.
Changes
- Introduction of debug API checker.
- Changes to improve “High Velocity Ghosting” situations.
- Changes to Luminance computation with pre-exposure application.
- Small motion vectors ignored in previous depth estimation.
- Changes to depth logic to improve disocclusion detection and avoid self-disocclusions.
- Dilated reactive mask logic updated to use temporal motion vector divergence to kill locks.
- New lock luminance resource.
- Accumulation overhauled to use temporal reactivity.
- Changed how intermediate signals are stored and tonemapped.
- Luminance instability logic improved.
- Tonemapping no longer applied during RCAS to retain more dynamic range.
- Fixes for multiple user reported issues on GitHub and elsewhere. Thank you for your feedback!
Via AMD