Altus Denoiser Release Roadmap

Innobright releases Altus on roughly a monthly schedule until Q2 2017. Below, you can see what features you’ll be seeing in the recent and upcoming point/patch releases.


Machine Learning Based Denoising

The most successful Monte Carlo denoising calculates the filter weights in a heuristic manner. Learning Based Filtering approaches this via the use of a neural network to automatically learn the complex relationship between a noisy scene and the ideal filter parameters, which is not possible via heuristic rules. The machine learning process will bring the next level of efficiency into the filtering of Monte Carlo images in a train and forget method such that the filter weights need not be calculated for each noisy image being filtered.

Real-time Denoising

The holy grail of denoising is to denoise an image in real time. From a performance standpoint, this is the final step in filtering of noise in Monte Carlo rendering, of course with the best possible quality. Innobright is working together with leading researchers in the field to crack this final frontier.