AMD GPUOpen FidelityFX FSR2 v2.2 Published
AMD's GPUOpen team has published the source code for their FidelityFX FSR2 v2.2 update. This update brings improved image quality for more cases, integration enhancements, a new debug API checker, and other refinements over the earlier FSR2 code.
Today's FidelityFX Super Resolution 2.2 publishing to GitHub contains their latest game upscaling tech and comes complete with a sample using the Cauldron framework.
The listed changes on GitHub with the FSR2 v2.2 update include:
- 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!
FidelityFX FSR2 v2.2 can be downloaded from GitHub.