Octane AI denoiser - initial tests, results and next steps

Forums: Octane AI denoiser - initial tests, results and next steps
Read about News and Updates regarding Octane Render in this forum.
Forum rules
For new users: this forum is moderated. Your first post will appear only after it has been reviewed by a moderator, so it will not show up immediately.
This is necessary to avoid this forum being flooded by spam.

Re: Octane AI denoiser - initial tests, results and next steps

Postby Goldorak » Wed Jul 19, 2017 3:27 pm

Goldorak Wed Jul 19, 2017 3:27 pm
3dworks wrote:can't wait for its release, hopefully it can be integrated well into plugins? will it work with networked GPU's?


We plan to just make it part of Octane itself (both local/cloud) once it's done. It will work through the Octane imager module system, which will include 1st party modules like this one shipping in all OR plug-ins.
User avatar
Goldorak
OctaneRender Team
OctaneRender Team
 
Posts: 2321
Joined: Sun Apr 22, 2012 8:09 pm

Re: Octane AI denoiser - initial tests, results and next steps

Postby pegot » Wed Jul 19, 2017 7:36 pm

pegot Wed Jul 19, 2017 7:36 pm
Is that a different denoiser than what we currently have or an enhancement to the existing system?
Win 10
3.7Ghz i9 10900k / 64GB
ASUS STRIX Z490-E
PSU: PowerSpec 850Wd
RTX 3090 Asus Tuff

Network rendering:
Win 10
4.2Ghz i7 7700k / 64GB
AsRock SuperCarrier
PSU: EVGA 1200w
RTX 3080 Ti EVGA Hybrid
RTX 3080 ASUS Tuff
GTX 1080ti SC Black (wc)
pegot
Licensed Customer
Licensed Customer
 
Posts: 921
Joined: Mon Nov 07, 2011 3:44 am

Re: Octane AI denoiser - initial tests, results and next steps

Postby Goldorak » Wed Jul 19, 2017 9:43 pm

Goldorak Wed Jul 19, 2017 9:43 pm
pegot wrote:Is that a different denoiser than what we currently have or an enhancement to the existing system?


Totally novel. Used machine learning.
User avatar
Goldorak
OctaneRender Team
OctaneRender Team
 
Posts: 2321
Joined: Sun Apr 22, 2012 8:09 pm

Re: Octane AI denoiser - initial tests, results and next steps

Postby calus » Fri Jul 21, 2017 2:30 pm

calus Fri Jul 21, 2017 2:30 pm
Goldorak wrote:We plan to just make it part of Octane itself (both local/cloud) once it's done. It will work through the Octane imager module system, which will include 1st party modules like this one shipping in all OR plug-ins.


Did Octane devs also investigated on the AI driven Adaptive sampling ?
Post-process denoising is not good for all production.
Can't the AI denoising feature also be used to produce a better noise map to drive adaptive sampling (instead of post process denoising) ?
It could bring to Octane better adaptive sampling a lot more efficient and less user input dependent...

Maybe the ultimate solution is to combine both AI driven Adaptive sampling and AI de-noising.
It seems to be the way Nvidia's Ai denoiser was implemented in IRAY:
"This isn’t just for interactive rendering at artist workstations, as a fully converged noiseless final frame renders is about four times faster; if a final render took an hour before, with the new AI it will take approximately 15 minutes."
https://www.fxphd.com/blog/whats-the-st ... w-iray-ai/
Pascal ANDRE
calus
Licensed Customer
Licensed Customer
 
Posts: 1308
Joined: Sat May 22, 2010 9:31 am
Location: Paris

Re: Octane AI denoiser - initial tests, results and next steps

Postby Goldorak » Sat Jul 22, 2017 2:38 am

Goldorak Sat Jul 22, 2017 2:38 am
calus wrote:
Goldorak wrote:We plan to just make it part of Octane itself (both local/cloud) once it's done. It will work through the Octane imager module system, which will include 1st party modules like this one shipping in all OR plug-ins.


Did Octane devs also investigated on the AI driven Adaptive sampling ?
Post-process denoising is not good for all production.
Can't the AI denoising feature also be used to produce a better noise map to drive adaptive sampling (instead of post process denoising) ?
It could bring to Octane better adaptive sampling a lot more efficient and less user input dependent...

Maybe the ultimate solution is to combine both AI driven Adaptive sampling and AI de-noising.
It seems to be the way Nvidia's Ai denoiser was implemented in IRAY:
"This isn’t just for interactive rendering at artist workstations, as a fully converged noiseless final frame renders is about four times faster; if a final render took an hour before, with the new AI it will take approximately 15 minutes."
https://www.fxphd.com/blog/whats-the-st ... w-iray-ai/


We're choosing to start with AI denoising in this way first for several reasons, but it is all possible on top of this and we're looking into all of it.
User avatar
Goldorak
OctaneRender Team
OctaneRender Team
 
Posts: 2321
Joined: Sun Apr 22, 2012 8:09 pm

Re: Octane AI denoiser - initial tests, results and next steps

Postby swipswap » Tue Aug 22, 2017 12:48 pm

swipswap Tue Aug 22, 2017 12:48 pm
Will this have an increased rendering speed on motion blurred areas or areas with heavy light scattering?
swipswap
Licensed Customer
Licensed Customer
 
Posts: 33
Joined: Thu Feb 12, 2015 12:35 am

Re: Octane AI denoiser - initial tests, results and next steps

Postby Goldorak » Wed Aug 23, 2017 7:34 am

Goldorak Wed Aug 23, 2017 7:34 am
swipswap wrote:Will this have an increased rendering speed on motion blurred areas or areas with heavy light scattering?


We are training it on DOF, MB and more, but it's very hard to measure real world success until we release a test build and see what user feedback tells us in aggregate (tuning will continue for many months after that I would expect).

So far it's doing well on random scenes we throw at it (10 - 50 samples) which are not in way related to the training samples. This is a critical test that has been passed. We're probably over the 50% mark towards a preliminary experimental release which users can help validate further.
User avatar
Goldorak
OctaneRender Team
OctaneRender Team
 
Posts: 2321
Joined: Sun Apr 22, 2012 8:09 pm

Re: Octane AI denoiser - initial tests, results and next steps

Postby ivankio » Sat Nov 11, 2017 12:10 am

ivankio Sat Nov 11, 2017 12:10 am
How is progress on the denoiser? Any estimates?
GTX 1080 8gb, GTX 970 4gb, I5 4590, Z97-E, 32gb RAM, Win 10 64bits, Octane for Maya
User avatar
ivankio
Licensed Customer
Licensed Customer
 
Posts: 103
Joined: Thu Nov 14, 2013 11:39 pm
Location: Curitiba - Brazil

Re: Octane AI denoiser - initial tests, results and next steps

Postby ivankio » Tue Nov 21, 2017 5:14 pm

ivankio Tue Nov 21, 2017 5:14 pm
I guess I can only hope your are not planning to push denoiser to 4.0.
GTX 1080 8gb, GTX 970 4gb, I5 4590, Z97-E, 32gb RAM, Win 10 64bits, Octane for Maya
User avatar
ivankio
Licensed Customer
Licensed Customer
 
Posts: 103
Joined: Thu Nov 14, 2013 11:39 pm
Location: Curitiba - Brazil

Re: Octane AI denoiser - initial tests, results and next steps

Postby Goldorak » Wed Nov 22, 2017 12:48 am

Goldorak Wed Nov 22, 2017 12:48 am
ivankio wrote:I guess I can only hope your are not planning to push denoiser to 4.0.


Unless something unexpected happens during the remaining integration work, we're planning to have the initial test release of the AI denoiser in 3.09.

As a caveat, that first release should be considered experimental tech. Getting it out to everyone by 3.09 (basically as soon as it's embedded in Octane), means we will not have had much time to do exhaustive testing prior to sharing it with the community for deeper QA.

The goal of getting this feature to users as soon as possible in 3.09 is to gather feedback on any corner cases ASAP (e.g. where denoising is too destructive), so we can further tune and improve the system's performance subsequent updates.

While the AI denoiser can do pretty awesome work, as in the tests and scenes we've shown, we may run into situations in real world usage where the AI isn't denoising correctly or usefully, or worse, goes Skynet on us once it discovers humanity is the root source of all unpredictable scene noise :D
User avatar
Goldorak
OctaneRender Team
OctaneRender Team
 
Posts: 2321
Joined: Sun Apr 22, 2012 8:09 pm
PreviousNext

Return to News & Announcements


Who is online

Users browsing this forum: No registered users and 10 guests

Thu Mar 28, 2024 6:51 pm [ UTC ]