Intel published the release of the project oidn 2.5 (Open Image Denoise), which develops a collection of filters for eliminating noise in images prepared using rendering systems based on ray tracing. Open Image Denoise is being developed as part of a larger project oneAPI Rendering Toolkit, aimed at developing software visualization tools for scientific calculations (SDVis (Software Defined Visualization), including a ray tracing library Embree, a photorealistic rendering system GLuRay, a distributed ray tracing platform OSPRay and a software rasterization system OpenSWR The code is written in C++ and published under the Apache 2.0 license.
The goal of the project is to provide high-quality, efficient and easy-to-use denoising functions that can be used to improve the quality of ray tracing results. The proposed filters allow, based on the result of a shortened ray tracing cycle, to obtain a final level of quality comparable to the result of a more expensive and a lengthy process for detailed rendering.
Open Image Denoise eliminates random noise that occurs, for example, during ray tracing based on numerical integration using the method Monte Carlo (MCRT). To achieve high quality rendering in such algorithms, it is necessary to trace a very large number of rays, otherwise noticeable artifacts in the form of random noise appear in the resulting image.
The use of Open Image Denoise allows you to reduce