AiTiles [Rev. 3] - AI Upscaled Terrain Tiles for Falcon BMS
-
@tad:
Hi Dodam,
How similar is your method to this one:
https://mrl.cs.nyu.edu/projects/image-analogies/That’s an ancient website and an ancient method (20 years in machine learning is a verrrry long time) – the paper doesn’t use any convolutions, nonlinear activations, or pooling, which are all hallmarks of modern deep learning. (I don’t know what year these started becoming popular – I know that some of them have existed since the 90s, at least.)
It’s a precursor, but I think about the only similarity is “filters are learned” – this is what my method is ripping off, though I have made pretty significant changes: https://arxiv.org/abs/1809.00219; it’s capable of doing some amazing things for game textures in general.
-
It’s a precursor, but I think about the only similarity is “filters are learned”
No, I fully understand that the link in my post is “ancient”. I wanted just to confirm that I understood your method with some added clarity.
-
Pretty nice initiative this yours, Dodam.
Thanks for sharing and your commitment. As just seems, major changes will happen in theater making in the next future, but until then… oh, who cares, after then, we will see how to apply all what we learned in these years about.
I’m just curious now to see how things will go even with my RTX 2080Ti, “ancient” if compared with your powerful 3090 (good purchase, BTW, well done this too!)
With best compliments and regards.
-
@tad:
No, I fully understand that the link in my post is “ancient”. I wanted just to confirm that I understood your method with some added clarity.
The “analogy” in this sense would be (2m res aerial photography : 0.5m resolution aerial photography) :: (512px terrain tiles : ?), but with a lot more going into the sausage.
I’m doing what’s called a “zero-shot generalisation”, which is just to say that the network never sees the terrain tiles in learning until it’s asked to actually upscale it for production – this is obviously necessary since I don’t have high resolution terrain tiles I can give the network as “this is what it should look like in the ideal case”. This relies on the terrain tiles looking similar to actual aerial photography, though there are techniques to help with generalisation. I might add another network that just focuses on photorealism (“take this 2048x2048 terrain tile, and make it look like a 2048x2048 aerial photograph”) in the future – the way to do that is to use another GAN, though I would really need to sit down and think about what the best way to do that would be since there’s only so many tiles.
Something that’s cool is that the night tiles are also a zero-shot generalisation – the SPUN-GAN has never seen a night tile (high resolution orthoimagery isn’t available for night scenes), but it seems know what to do with night tiles without being explicitly taught.
-
Thanks for sharing and your commitment. As just seems, major changes will happen in theater making in the next future, but until then… oh, who cares, after then, we will see how to apply all what we learned in these years about.
Heh – if nothing else, I hope this can reduce the workload for theatrebuilders. How are they changing?
Also, if you need an accurate OOB for ROK with approximate locations at the battalion level, I’m happy to translate that from what’s available publicly on Korean wikis. There’s also a bunch of spelling errors / border inaccuracies in the KTO.
-
That’s just the conclusion I’d wish to hear, dear Dodam.
And, about your kind proposal, my huge thanks in advance if you don’t bother to do that… it would be simply great and one more valuable gift.
Even more valuable for a mission creating addict as, on my little own, I think I am.With best regards.
-
I’ll probably only be able to do it once the theatre creation is stable, but it’ll be something to do in the future (though I have no clue if the campaign / 3D engine can handle realistic OOBs – the ROKA has 37 divisions and 30 brigades unattached to a division).
-
Looks very good, well done! Will there be any issues for multiplayer use ?
-
Looks very good, well done! Will there be any issues for multiplayer use ?
textures have no effects on mp
-
Looks very good, well done! Will there be any issues for multiplayer use ?
I guess there won’t be crashing issues from what dema has said, but visual cues might look a little different – e.g. you might be able to recognise roads a bit more than the rest of your package, so if you give directions to other people for a visual target relative to that road, it might be just slightly harder to spot the target.
There is also a small chance that the network does something weird (e.g. it sees what’s supposed to be a blue slate roof and turns it into a swimming pool). I don’t think it should be an issue overall though!
-
Job well done……Much appreciated!
-
Okay, I have uploaded Rev. 1 (the screenshots have also been updated)– I don’t think I’ll make significant changes to the architecture now, but more training should help. Try it and let me know what you think! (Note: There’s some artifacts around tile borders of the tiles – they’ll be fixed with the next revision.)
-
The link suffers from its success =).
-
I’d be happy to help host a torrent.
Cheers, Uwe
-
I just tested it today and I noticed ; some tiles are missing and we can see the border of each tiles ( visible with the LGB training TE)
original:
Mod:
-
Some of the night tiles were porked. Maybe not present in the new “mod” set.
-
I just tested it today and I noticed ; some tiles are missing and we can see the border of each tiles ( visible with the LGB training TE)
@tad:
Some of the night tiles were porked. Maybe not present in the new “mod” set.
Oops, I think I forgot to copy the old tiles into the modded tiles for Rev. 1 – I don’t touch the tiles that aren’t 512x512 (I think there are 200 tiles that are either larger or smaller than that out of ~7100), so not all tiles get upscaled. I’ll post a version that has this fixed in a few hours. (The tile borders thing is mostly an artifact from not having enough context, but I’m working on fixing that too.)
Thanks for the feedback!
-
The tile borders thing is mostly an artifact from not having enough context, but I’m working on fixing that too
Perhaps to save on your time this could be solved by knowing how the seamless borders are obtained in the basic/original set.
-
@tad:
Perhaps to save on your time this could be solved by knowing how the seamless borders are obtained in the basic/original set.
In the original, I think the tile creators just build as a set of 16 – that’s not something I can do, though. (It wouldn’t fit in the GPU to begin with.) The network sees a context of 48x48 pixels for each pixel at low resolution, so it can get a little confused at the edges (where half of that information just doesn’t exist).
-
Finally I can download. But I suppose it’s a matter of hours before I redo it.