ALTUS DENOISER RELEASE ROADMAP
Innobright is working on the bleeding edge of denoising technology. We are commited to pushing the limit of what’s possible with denoising in both quality and speed. At Siggraph 2017, we had a chance to meet with the other players in the industry and compile an updated roadmap.
Here are some milestones in our roadmap for Altus:
Parameter Optimization – Altus is a powerhouse of a denoiser. The various parameters in Altus are tweaked to give the best results across all supported renderers. In the future, we expect to optimize and tune these parameters on a per-render basis. This will give even better results right out of the box for every render.
Machine Learning Based Denoising – Machine Learning Based denoising is the most exciting advancement in denoising since it’s creation. A Learning Based approach via the use of neural networks will automatically learn the complex relationship between a neighborhood of noisy pixels and the ‘ground truth’ resulting pixel. The machine learning process will bring the next level of efficiency into the filtering of Monte Carlo images.
Interactive Denoising – The holy grail of denoising is to denoise an image in real time or interactive frame rates. This is the final step in filtering of noise in Monte Carlo rendering from a performance standpoint. Of course, the fastest denoiser is only as useful as the quality it outputs. Innobright is working together with leading researchers in the field to crack this final frontier in both performance and quality.
Stay tuned for more product updates that will lead to this point.
If you are looking for more technical information about the changes happening to Altus, view our Change Log in our Help Documentation.
REMOVE THE WATERMARK
All Altus downloads, including our SDK, are free for evaluation purposes, but insert a watermark over your render. To remove the watermark, purchase the licenses you'll need to get your project finished quickly.
If you want to say goodbye to expensive, slow 3-D renders, check out what Altus can do.