Save Rendering Time & Increase Image Quality with Free Open Source Library

Graphics developers routinely face a tradeoff when using ray tracing to create realistic, immersive experiences: allow for the hours (and hours) it takes to render high-quality images or use denoising methods to produce less-than-high-quality images … but do it a lot faster.

Intel® Open Image Denoise can remove this dilemma.

It’s an open source library of high-performance, high-quality, machine-learning-based denoising filters for images rendered with ray tracing. Part of the Intel® oneAPI Rendering Toolkit, this library is suitable for both interactive and final-frame rendering, runs on almost any Intel CPU, and significantly reduces rendering times.

It’s also completely free.

Join Graphics Software Engineer Attila Afra for a detailed session that will include:

  • The importance and impact of denoising when rendering images with ray tracing
  • How Intel Open Image Denoise achieves high-quality denoising using machine learning (hint: it filters out the Monte Carlo noise)
  • How to use the simple, flexible C/C++ API to integrate denoising into existing renderers in hours or even minutes
  • Training the denoising neural networks yourself to achieve even higher quality for your renderer or implement custom filters

Get the software

Get Intel® Open Image Denoise as part of the Intel® oneAPI Rendering Toolkit—five free libraries for developing photorealistic applications.

Attila Afra, Graphics Software Engineer, Intel Corporation

Attila Áfra is a Graphics Software Engineerwho leads development of the Intel® Open Image Denoise library, and also works on the Intel® Embree ray tracing kernel library and the Intel® OSPRay ray tracing engine. He joined Intel in 2015 and his research interests include rendering, image processing, and parallel programming. Attila holds BSc and MSc degrees in computer science, and completed his PhD in Computer Graphics (specifically on high-performance ray tracing methods for CPUs) at Babes-Bolyai University in Cluj-Napoca, Romania.

Performance varies by use, configuration, and other factors. Learn more at