Intel published the production of the project oidn 2.2 (Open Image Denoise), developing a collection of filters to eliminate noise in images prepared using ray trace-based systems. Open Image Denoise is developing as part of a larger project oneAPI rendering toolkit aimed at developing software visualization calculations (sdvis), including the library of rays trace embree, a system of photorealistic rendering gluray, a distributed ray trace platform Ospray, and the system of software rasterization OpenSWR. The code is written in C++ and published under the Apache 2.0 license.
The purpose of the project is to provide high-quality, effective, and easy-to-use noise reduction functions that can be used to improve the quality of ray trace results. The proposed filters allow, based on the result of the abbreviated cycle of ray tracing, to achieve a final level of quality comparable to the result of a more costly and time-consuming detailed rendering process.
Open Image Denoise ensures the removal of random noise that occurs, for example, when tracing rays based on numerical integration by the method Monte Carlo (MCRT). To achieve high-quality rendering in such algorithms, a very large number of rays must be traced, otherwise noticeable artifacts in the form of random noise appear in the resulting image.
The use of Open Image Denoise allows for a significant reduction in the number of necessary calculations by several orders when calculating each