Duke4.net Forums: PolymerRTX - Duke4.net Forums

Jump to content

  • 8 Pages +
  • « First
  • 5
  • 6
  • 7
  • 8
  • You cannot start a new topic
  • You cannot reply to this topic

PolymerRTX

User is offline   Paul B 

#181

Guys i'm sure when he has time he will update us. IceColdDuke owes us nothing but he comes with a lot of experience and when he does do things he is fast at it. Who knows, maybe his expensive RTX video card went up in flames? Seems to be a trend these days.
0

User is offline   Forge 

  • Speaker of the Outhouse

#182

View PostPaul B, on 07 December 2018 - 12:34 PM, said:

Guys i'm sure when he has time he will update us. . Who knows,


2

User is offline   OpenMaw 

  • Judge Mental

#183

View PostTea Monster, on 07 December 2018 - 10:09 AM, said:

Yeah,I know the guy, he's the one that fooled us FIVE times. What does that make us?


The...Five finger...em...Death... Punch?
0

User is offline   Mark 

#184

It would be nice if he could at the very least spend 20 seconds to post I'm alive and well but work has suspended or I'm working on it and staying away from the distractions of Duke4net for now. Its the unexplained absences that bug us/me.

This post has been edited by Mark: 07 December 2018 - 01:37 PM

2

User is offline   Jmoc 

#185

There are two fundamental flaws within those projects:

1. It all begins with an ambitious objective full pf promises, usually very specific, not easily scalable or completely cross-platform, which needs a lot of work for even its planned first step.
2. Then, development is an one-man businness, with no open access repository to work on it.


The inevitable outcome is that when the developer quits, no one can possibily catch up to it. And it happens all the time.


Take HRP as a counterexample. HRP is a HUGE project which 1. could be started even with one single, proof of concept updated art and 2. everyone can contribute to some extent.

Consider also Polymer. It already runs on every (powerful enough) machine, and its source its completely open. Every effort put into Polymer will have immediate repercussions on the userbase using it.


The take away message is: beware of the projects described above. To me, it is MUCH more enjoyable to put hope inside a slow, minor but well-posed project instead of hanging on somebody's word.

My 2 cents.
2

User is offline   Mark 

#186

And that goes back to what Teamonster has brought up many times. There doesn't seem to be people well versed in renderers that want anything to do with Eduke32. So the saga continues.

This post has been edited by Mark: 08 December 2018 - 12:17 PM

1

User is offline   TerminX 

  • el fundador

  #187

Hey, at least this time we got him to do something useful for us that we ended up merging into SVN, even if it was just proper Visual Studio solution and project files so we could ditch our 15-year-old makefile.
3

User is offline   NightFright 

  • The Truth is in here

#188

Could have told before it's gonna happen. Oh well.
0

User is offline   TerminX 

  • el fundador

  #189

He has some serious shit going on in his life. I fully believe he means well.
4

User is offline   VGA 

#190

Who was the main developer of the Polymer renderer? Was it icecoldduke? Cause it's good.
0

User is offline   MusicallyInspired 

  • The Sarien Encounter

#191

Plagman. I don't think Icecoldduke was around back then.

This post has been edited by MusicallyInspired: 08 December 2018 - 06:35 PM

0

#192

Just a quick update, I'm experimenting with Neural Networks for graphics using RTX, and tried to apply it to image upscaling. I upscaled all the original tiles by 4x using this technique. Here are the results.

Posted Image
Posted Image
Posted Image

This post has been edited by icecoldduke: 21 January 2019 - 01:49 PM

7

User is offline   Paul B 

#193

View Posticecoldduke, on 21 January 2019 - 01:49 PM, said:

Just a quick update, I'm experimenting with Neural Networks for graphics using RTX, and tried to apply it to image upscaling. I upscaled all the original tiles by 4x using this technique. Here are the results.

Posted Image
Posted Image
Posted Image


Wow !!! I don't have an artistic eye and I can clearly see the difference! That's amazing!
0

User is online   Phredreeke 

#194

I think the sprites need some form of edge antialiasing
1

User is offline   MusicallyInspired 

  • The Sarien Encounter

#195

I believe you're the first person to attempt this during run-time. Interesting results. Could use some work of course, but promising.
0

User is offline   Kyanos 

#196

View Posticecoldduke, on 21 January 2019 - 01:49 PM, said:

Just a quick update, I'm experimenting with Neural Networks for graphics using RTX, and tried to apply it to image upscaling. I upscaled all the original tiles by 4x using this technique. Here are the results.

Can you please share those sprites with the community? Or just me is fine :)
0

User is offline   MusicallyInspired 

  • The Sarien Encounter

#197

View PostPhotonic, on 21 January 2019 - 03:29 PM, said:

Can you please share those sprites with the community? Or just me is fine :)


They're upscaled by the engine during run-time. He doesn't have a library of upscaled sprites....at least I don't think he does. If he did why would he even post this as "progress?" His renderer is upscaling the low-res vanilla sprites on the fly.
0

User is offline   NightFright 

  • The Truth is in here

#198

What I would like to know: What's the impact on your FPS with this feature activated?
0

#199

View PostMusicallyInspired, on 21 January 2019 - 10:38 PM, said:

They're upscaled by the engine during run-time. He doesn't have a library of upscaled sprites....at least I don't think he does. If he did why would he even post this as "progress?" His renderer is upscaling the low-res vanilla sprites on the fly.

To be clear, this isn't real time. So yes I have a huge collection of AI upscaled tiles sitting on my hard drive. So why is this "progress"? I actually started doing this because I wanted to figure out how the core part of DLSS could work(since there really isn't a lot of documentation on how it works). There are tools out there now, that you can use to do AI upscaling, but I guess the cool part is, I figured it out myself :), which isn't something I should have called "progress", so sorry, but I'm excited that I figured it out(yay me :lol:) Also this is my first time using a neural network that generated some pretty cool results, that executes on the RTX hardware.

But no I'm not releasing a sprite dump because I'm pretty sure that's illegal :D.

Let me catch everyone up on what I've been up too. This past month has mostly been about, how can I use RTX as a development acceleration tool. So a couple things came to mind for testing, image upscaling(see above) and lightmapping. Both bits have been done for years, but not with hardware acceleration. So I made a Return to Castle Wolfenstein lightmapper that can fully light a map, that has 571 lights, in about 6.5 seconds, at 4k. The lighting results in this scene don't match the original(I'm doing some testing where I needed to exaggerate some lights, I post some more stuff when I get back to the U.K.). The trashed looking triangles are because I'm not handling Quake's tessellated surfaces properly.
Posted Image

So how does all of this apply to PolymerRTX? I'm trying to see if I can expand the renderer out, so devs might require a 2080 to make a map for PolymerRTX, but you can use a 2060 to play. Essentially light baking using a properly trained neural network. I don't know if this can work, I'm essentially in uncharted territory. So basically the above two projects are basically me trying to learn two very complicated concepts, and coming with a new type of rendering idea, and it might not work out, but what I learn here can translate into something more tangible.

I have to head out to my flight, but I'll try to catch you guys up on the idea when I can, I'm sorry I've just been traveling all over the place as of late.

This post has been edited by icecoldduke: 22 January 2019 - 01:54 AM

2

User is offline   Kyanos 

#200

>But no I'm not releasing a sprite dump because I'm pretty sure that's illegal :).

Release it under the HRP license.
Attached File  hrp_art_license.txt (3.47K)
Number of downloads: 144
Spoiler

1

User is online   Danukem 

  • Duke Plus Developer

#201

View PostPhotonic, on 22 January 2019 - 11:50 AM, said:

>But no I'm not releasing a sprite dump because I'm pretty sure that's illegal :).

Release it under the HRP license.



But it's not the HRP, it's the actual game textures upscaled. When they made the HRP they were specifically told not to simply upscale images -- I'm pretty sure the HRP license was negotiated only for the HRP.
0

User is offline   MusicallyInspired 

  • The Sarien Encounter

#202

View Posticecoldduke, on 22 January 2019 - 12:24 AM, said:

To be clear, this isn't real time. So yes I have a huge collection of AI upscaled tiles sitting on my hard drive. So why is this "progress"? I actually started doing this because I wanted to figure out how the core part of DLSS could work(since there really isn't a lot of documentation on how it works). There are tools out there now, that you can use to do AI upscaling, but I guess the cool part is, I figured it out myself :), which isn't something I should have called "progress", so sorry, but I'm excited that I figured it out(yay me :lol:) Also this is my first time using a neural network that generated some pretty cool results, that executes on the RTX hardware.


Oh.
0

User is online   Vagan 

#203

Hey ICD, good to see you back. Great stuff!

This post has been edited by Vagan: 22 January 2019 - 07:57 PM

0

User is offline   Micky C 

  • Honored Donor

#204

View Posticecoldduke, on 21 January 2019 - 01:49 PM, said:

Just a quick update, I'm experimenting with Neural Networks for graphics using RTX, and tried to apply it to image upscaling. I upscaled all the original tiles by 4x using this technique. Here are the results.


What renderer are you using for those pics? I assume it's not polymerRTX.
0

#205

View Posticecoldduke, on 22 January 2019 - 12:24 AM, said:

But no I'm not releasing a sprite dump because I'm pretty sure that's illegal :).

Any distribution of copyrighted materials is illegal, but in practice, plenty of people are using ML to upscale textures and releasing mod packs left and right.

https://captrobau.bl...a-released.html

Even if you don't release your pack, someone else may end up recreating them and releasing them.
0

#206

So just a little bit of an update, I'm continuing to try and train the neural network to deal with some of the graphics errors I've found when processing Duke3D sprites. I'm getting close to releasing something for you guys to run on your end, to test and get feedback. For additional neural network training, I've been grabbing a lot of old game data, manually creating some hd textures, and training the network to create my shitty hd version of various things :). It's going well. I know you guys want to see want to see more Duke bits, and hopefully I'll have more to show after I train the neural net a bit more. In the mean time, here is some progress. I can take Iron Helix, that is a Myst style adventure game, were everything is rendered as pre-rendered movies approx. 162x122), and 4x it's size while adding detail. I'm still getting some consistent edge case fails, across all games I've thrown at this(space and planets don't seem to come through properly for example), anyway here are some screens.

As I side note, I must have played the intro cinematic 1000's of times as a kid, and I never realized there was a smiley face easter egg on the radar screen, that represented the planet the ship was about to destroy. I've found quite a lot of interesting things running various games through this tool.

Posted Image

Posted Image

Posted Image

Posted Image



This post has been edited by icecoldduke: 10 March 2019 - 12:38 PM

1

User is offline   Micky C 

  • Honored Donor

#207

Nice to see this is moving along. The comparisons look promising.

I take it you’ve spent your time on the upscale side, as opposed to the ray-tracing side?

This post has been edited by Micky C: 10 March 2019 - 02:40 PM

0

User is online   Danukem 

  • Duke Plus Developer

#208

View Posticecoldduke, on 10 March 2019 - 12:37 PM, said:

So just a little bit of an update, I'm continuing to try and train the neural network to deal with some of the graphics errors I've found when processing Duke3D sprites. I'm getting close to releasing something for you guys to run on your end, to test and get feedback.


How does this relate to PolymerRTX, exactly? Phredreeke has a good process now for producing 2X upscales of sprites using ESRGAN and lots of post-processing steps, which some of us are already using. Maybe what you are doing is even better, I dunno, but I'm just confused as to how PolymerRTX suddenly became an upscaled sprite project.
0

User is offline   Mark 

#209

"They're upscaled by the engine during run-time"...quoted from some previous post
0

User is online   Phredreeke 

#210

View Posticecoldduke, on 22 January 2019 - 12:24 AM, said:

To be clear, this isn't real time. So yes I have a huge collection of AI upscaled tiles sitting on my hard drive. So why is this "progress"? I actually started doing this because I wanted to figure out how the core part of DLSS could work(since there really isn't a lot of documentation on how it works). There are tools out there now, that you can use to do AI upscaling, but I guess the cool part is, I figured it out myself :), which isn't something I should have called "progress", so sorry, but I'm excited that I figured it out(yay me :D) Also this is my first time using a neural network that generated some pretty cool results, that executes on the RTX hardware.

0

Share this topic:


  • 8 Pages +
  • « First
  • 5
  • 6
  • 7
  • 8
  • You cannot start a new topic
  • You cannot reply to this topic


All copyrights and trademarks not owned by Voidpoint, LLC are the sole property of their respective owners. Play Ion Fury! ;) © Voidpoint, LLC

Enter your sign in name and password


Sign in options