It is currently 15 Oct 2018, 08:13
   
Text Size

Upscale low res card images to high res using Deep Learning

Discuss Card Scans and Other Artwork Here

Moderator: CCGHQ Admins

Re: Upscale low res card images to high res using Deep Learn

Postby Huggybaby » 06 Jan 2018, 23:00

Sorry for the questions, but I'm not tuned in like I used to be...

How much time between Gatherer and HQ releases? HQ requires card acquisition and the time for that varies a lot but I don't know by how much lately, charlequin would know but since we're talking already I thought I should ask. lol

Also, these processed pics look really good but are smaller than yours and have less artifacts:
viewtopic.php?f=26&t=16678&start=120#p221247

Can you fill me in? Or Bog Wraith?

I guess what I'm asking is what's going on with the LQ Pics scene?
User avatar
Huggybaby
Administrator
 
Posts: 3076
Joined: 15 Jan 2006, 19:44
Location: Finally out of Atlanta
Has thanked: 571 times
Been thanked: 570 times

Re: Upscale low res card images to high res using Deep Learn

Postby austinio7116 » 06 Jan 2018, 23:05

Looks like that other thread is using Waifu - a more generic anime upsampling tool that does a great job on art and gives a really smooth result, but less sharp than mine - it is trained on anime images rather than specifically magic cards, but is probably trained on a larger dataset for longer. I prefer my results at the resolution I used them at, but that could be a matter of taste.

I'm not sure what the lead time on HQ releases is.
User avatar
austinio7116
 
Posts: 380
Joined: 10 Mar 2017, 11:59
Has thanked: 47 times
Been thanked: 123 times

Re: Upscale low res card images to high res using Deep Learn

Postby Huggybaby » 06 Jan 2018, 23:31

I love the way your pics look. But the thing that really draws my attention is at the bottom of the card where the credits and copyright are, that's where I have always immediately looked to assess processing quality. In the waifu everything looks clear even zoomed larger than yours but the Deep Learning has obvious artifacts.

I hope you're not offended by the observation because I don't mean to disrespect, or to waltz in here johnny come lately and tell you anything. Plus, I could be doing something wrong. NTM my ignorance.
User avatar
Huggybaby
Administrator
 
Posts: 3076
Joined: 15 Jan 2006, 19:44
Location: Finally out of Atlanta
Has thanked: 571 times
Been thanked: 570 times

Re: Upscale low res card images to high res using Deep Learn

Postby austinio7116 » 06 Jan 2018, 23:33

It has been a problem to get that footer text looking good. Something about it seems to cause the network to really struggle.

With all the different parameters I tried, this current version is the best I have managed for the footer text. If I ever get time to revisit the model and training it would be an area to focus on.
Last edited by austinio7116 on 06 Jan 2018, 23:42, edited 1 time in total.
User avatar
austinio7116
 
Posts: 380
Joined: 10 Mar 2017, 11:59
Has thanked: 47 times
Been thanked: 123 times

Re: Upscale low res card images to high res using Deep Learn

Postby austinio7116 » 06 Jan 2018, 23:35

Just for completeness, the Waifu algorithm is very similar, it also uses deep convolutional neural networks, just with a different model and different training data.
User avatar
austinio7116
 
Posts: 380
Joined: 10 Mar 2017, 11:59
Has thanked: 47 times
Been thanked: 123 times

Re: Upscale low res card images to high res using Deep Learn

Postby Huggybaby » 06 Jan 2018, 23:55

Thank you. Do you mask out areas of the card so you can use different parameters for different parts?
User avatar
Huggybaby
Administrator
 
Posts: 3076
Joined: 15 Jan 2006, 19:44
Location: Finally out of Atlanta
Has thanked: 571 times
Been thanked: 570 times

Re: Upscale low res card images to high res using Deep Learn

Postby austinio7116 » 06 Jan 2018, 23:56

Not currently, I leave the network to learn whatever it needs to learn, that is the joy of deep learning. Perhaps some hand holding would help, but it might make it less generic to different card frames etc.
User avatar
austinio7116
 
Posts: 380
Joined: 10 Mar 2017, 11:59
Has thanked: 47 times
Been thanked: 123 times

Re: Upscale low res card images to high res using Deep Learn

Postby Bog Wraith » 07 Jan 2018, 00:32

Huggybaby wrote:Sorry for the questions, but I'm not tuned in like I used to be...

How much time between Gatherer and HQ releases? HQ requires card acquisition and the time for that varies a lot but I don't know by how much lately, charlequin would know but since we're talking already I thought I should ask. lol

Also, these processed pics look really good but are smaller than yours and have less artifacts:
viewtopic.php?f=26&t=16678&start=120#p221247

Can you fill me in? Or Bog Wraith?

I guess what I'm asking is what's going on with the LQ Pics scene?
The last set was one of the fastest turn arounds I can remember. I expect that this new set will also be available in HQ relatively soon after release. In the meantime, this upscale method gives us a really fine look to play with and I am most impressed with the software that does this. I agree that the bottom of the card's text is the weakest part of this process & I hope that austinio will be able to tweak it as we go forward, but this is such a wonderful step upward in quality that we can play with while we await the HQ release(s).

Nice to see you, my old friend. I trust you & yours are doing well & I wish you all the best in 2018! :)
'Twas in the bogs of Cannelbrae
My mate did meet an early grave
'Twas nothing left for us to save
In the peat-filled bogs of Cannelbrae.
User avatar
Bog Wraith
Global Mod 1 (Ret)
 
Posts: 1075
Joined: 28 May 2008, 22:40
Location: Shandalar
Has thanked: 392 times
Been thanked: 148 times

Re: Upscale low res card images to high res using Deep Learn

Postby Huggybaby » 07 Jan 2018, 14:33

Thank you Bog Wraith. Yeah, we're still hanging on by our fingernails. :)
(Oh, and really enjoying this cold-a** weather you sent our way.)

Happy New Year brother!
User avatar
Huggybaby
Administrator
 
Posts: 3076
Joined: 15 Jan 2006, 19:44
Location: Finally out of Atlanta
Has thanked: 571 times
Been thanked: 570 times

Re: Upscale low res card images to high res using Deep Learn

Postby Bog Wraith » 07 Jan 2018, 16:44

Huggybaby wrote:Thank you Bog Wraith. Yeah, we're still hanging on by our fingernails. :)
(Oh, and really enjoying this cold-a** weather you sent our way.)

Happy New Year brother!
LOL!

Yeah, sorry about that one my brother. There are lizards falling out of the trees in Florida, FROZEN to death!

Climate change means just that, not that it is always getting hotter, which it is as the global temps continue to rise, but it means weather patterns are changing and out of the norm. This is just the beginning and things are going to get a lot worse, especially for the kids of tomorrow.

Stay warm my friend and think thoughts as I do, that pitchers & catchers report for Spring Training in a month or so.

Baseball is my salvation! 8)
Attachments
attv5.jpg
'Twas in the bogs of Cannelbrae
My mate did meet an early grave
'Twas nothing left for us to save
In the peat-filled bogs of Cannelbrae.
User avatar
Bog Wraith
Global Mod 1 (Ret)
 
Posts: 1075
Joined: 28 May 2008, 22:40
Location: Shandalar
Has thanked: 392 times
Been thanked: 148 times

Re: Upscale low res card images to high res using Deep Learn

Postby Fizanko » 19 Jan 2018, 01:00

I can't believe i didn't spotted this thread before.
And the less i can say is that i'm very impressed by how good the processed pictures are considering they're coming from a low resoluton original.
Fantastic work !
Innistrad world for Forge (updated 17/11/2014)
Duel Decks for Forge - Forge custom decks (updated 25/10/2014)
User avatar
Fizanko
Tester
 
Posts: 766
Joined: 07 Feb 2014, 11:24
Has thanked: 154 times
Been thanked: 85 times

Re: Upscale low res card images to high res using Deep Learn

Postby Bog Wraith » 27 Jan 2018, 16:43

The Commander Anthology set, or CMA, as you can see below, is only available in a very sub par scan AFAIK.

Not sure if your method can do anything with these as they are so blurry to begin with, but I'm posting this link so you can give it a go if you deem that they are even worth the effort. :roll:

All the images have the .full extension as that are used in Forge.

http://www.mediafire.com/file/438lbh53hdjduf2/CMA.zip
Attachments
Corpse Augur.full.jpg
'Twas in the bogs of Cannelbrae
My mate did meet an early grave
'Twas nothing left for us to save
In the peat-filled bogs of Cannelbrae.
User avatar
Bog Wraith
Global Mod 1 (Ret)
 
Posts: 1075
Joined: 28 May 2008, 22:40
Location: Shandalar
Has thanked: 392 times
Been thanked: 148 times

Re: Upscale low res card images to high res using Deep Learn

Postby austinio7116 » 27 Jan 2018, 19:01

As those cards are lower than the 370x265 my network is trained on, I thought I'd try Waifu to upsample to 370x265 then put them through my network. Here are the results:

Low Res

Image.png


Waifu

Image_waifu2x_art_noise1_scale_tta_1 (1).png


Waifu + SREZ

Image_waifu2x_art_noise1_scale_tta_1.png.xhlq.png
Attachments
Image_waifu2x_art_noise1_scale_tta_1.png
User avatar
austinio7116
 
Posts: 380
Joined: 10 Mar 2017, 11:59
Has thanked: 47 times
Been thanked: 123 times

Re: Upscale low res card images to high res using Deep Learn

Postby austinio7116 » 27 Jan 2018, 19:05

I don't think adding my network on top of Waifu helps - I'd suggest either using Waifu (which is a more generic upsampling network), or I'd have to re-train my network for these lower res images which I don't really have time for at the moment.
User avatar
austinio7116
 
Posts: 380
Joined: 10 Mar 2017, 11:59
Has thanked: 47 times
Been thanked: 123 times

Re: Upscale low res card images to high res using Deep Learn

Postby austinio7116 » 26 Feb 2018, 19:30

Jace, the Mind Sculptor.full.png
User avatar
austinio7116
 
Posts: 380
Joined: 10 Mar 2017, 11:59
Has thanked: 47 times
Been thanked: 123 times

PreviousNext

Return to Pictures

Who is online

Users browsing this forum: No registered users and 6 guests

cron

Who is online

In total there are 6 users online :: 0 registered, 0 hidden and 6 guests (based on users active over the past 10 minutes)
Most users ever online was 279 on 11 Jul 2013, 22:03

Users browsing this forum: No registered users and 6 guests

Login Form