Intel's Open Image Denoiser (OIDN) is an open-source library that uses the GPU for the "denoising process" which has been updated to include support for its upcoming Arrow Lake and Lunar Lake chips with integrated GPUs, as well as its next-gen Battlemage "Xe2" GPU.
The denoising technology removes grain and artifacts in a ray-tracing rendered image using multiple algorithms, preserving the original image quality and fidelity. OIDN includes faster rendering times, with the "noise" being removed, hardware resources are used in the best way possible.
Intel's new OIDN v2.3 supports new CPU architectures with Arrow Lake and Lunar Lake, as well as Battlemage "Xe2" GPUs coming later this year. The updated OIDN software has 1.5x to 2x speed improvements in real-time previews using the high-quality mode.
Intel's upcoming Arrow Lake processors have integrated GPUs based on the upgraded Alchemist+ or Xe-LPG+ architecture, while Lunar Lake rocks next-gen Battlemage "Xe2" GPU cores that have a huge 50% performance boost over Alchemist "Xe" GPUs.
The release notes explain the changes, released on GitHub:
- Significantly improved image quality of the RT filter in high quality
- mode for HDR denoising with prefiltering, i.e., the following combinations
- of input features and parameters:
- - HDR color + albedo + normal + cleanAux
- - albedo
- - normal
- In these cases a much more complex filter is used, which results in lower
- performance than before (about 2x). To revert to the previous performance
- behavior, please switch to the balanced quality mode.
- Added fast quality mode (OIDN_QUALITY_FAST) for even higher performance
- (about 1.5-2x) interactive/real-time previews and lower default memory usage
- at the cost of somewhat lower image quality. Currently this is implemented
- for the RT filter except prefiltering (albedo, normal). In other cases
- denoising implicitly falls back to balanced mode.
- Added Intel Arrow Lake, Lunar Lake, and Battlemage GPU support
