It is currently 12 Dec 2017, 18:06
   
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 austinio7116 » 16 Sep 2017, 20:15

I have prepared the images for Forge - so they are on the ftp server ready for download in Forge once it is updated.
Last edited by austinio7116 on 16 Sep 2017, 20:53, edited 1 time in total.
austinio7116
 
Posts: 180
Joined: 10 Mar 2017, 11:59
Has thanked: 20 times
Been thanked: 57 times

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

Postby austinio7116 » 16 Sep 2017, 20:20

Here are the upsampled XLN tokens. I had to use 2 zips to keep under 2MB.
Attachments
tokens300dpi-2.zip
(1.72 MiB) Downloaded 21 times
tokens300dpi.zip
(1.72 MiB) Downloaded 22 times
austinio7116
 
Posts: 180
Joined: 10 Mar 2017, 11:59
Has thanked: 20 times
Been thanked: 57 times

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

Postby Halian » 16 Sep 2017, 20:50

austinio7116 wrote:I have prepared the images for Forge - you should be able to get them here:

ftp://cardforge.org/zeny/300dpi%20images/XLN
I can't access the images, as the server asks me to log in.
Halian
 
Posts: 1
Joined: 16 Sep 2017, 20:38
Has thanked: 1 time
Been thanked: 0 time

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

Postby MaxMtg » 16 Sep 2017, 20:50

austinio7116 wrote:I have prepared the images for Forge - you should be able to get them here:

ftp://cardforge.org/zeny/300dpi%20images/XLN
This url asks for an ID and password , login credentials from CCGH do not work on this!
Last edited by MaxMtg on 16 Sep 2017, 20:52, edited 1 time in total.
MaxMtg
 
Posts: 36
Joined: 11 Aug 2017, 16:11
Has thanked: 22 times
Been thanked: 0 time

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

Postby austinio7116 » 16 Sep 2017, 20:51

austinio7116
 
Posts: 180
Joined: 10 Mar 2017, 11:59
Has thanked: 20 times
Been thanked: 57 times

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

Postby Bog Wraith » 17 Sep 2017, 05:03

To have images of this quality, a week before even the pre release no less, is very much appreciated and I thank you for the time and effort you've put into this project!

It's wonderful to use them right away in my first draft of this set in Forge.

Thank you, again.

---------------------
EDIT

Not sure if you have these, but in case you don't, here are the LQ images for Iconic Masters:

http://www.mediafire.com/file/z05jj590w ... IMA_LQ.zip
'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: 1048
Joined: 28 May 2008, 22:40
Location: Shandalar
Has thanked: 347 times
Been thanked: 147 times

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

Postby austinio7116 » 17 Sep 2017, 05:29

Thanks - I'll get them going through the network.

- processing now
Last edited by austinio7116 on 17 Sep 2017, 07:11, edited 1 time in total.
austinio7116
 
Posts: 180
Joined: 10 Mar 2017, 11:59
Has thanked: 20 times
Been thanked: 57 times

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

Postby austinio7116 » 17 Sep 2017, 05:33

"It's wonderful to use them right away in my first draft of this set in Forge."

That was always my goal - and I will continue to release these early upsampled images even though we may see scans released earlier again now. Huge praise should go to the Forge dev team though for their efforts getting the cards scripts up so quickly this cycle.
austinio7116
 
Posts: 180
Joined: 10 Mar 2017, 11:59
Has thanked: 20 times
Been thanked: 57 times

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

Postby MaxMtg » 17 Sep 2017, 10:43

Could you consider doing this for Commander 2017 as well?
MaxMtg
 
Posts: 36
Joined: 11 Aug 2017, 16:11
Has thanked: 22 times
Been thanked: 0 time

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

Postby austinio7116 » 17 Sep 2017, 11:11

I'll rerun those with the latest version soon.
austinio7116
 
Posts: 180
Joined: 10 Mar 2017, 11:59
Has thanked: 20 times
Been thanked: 57 times

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

Postby Agetian » 18 Sep 2017, 06:59

Very nice, keep up the great job!
Iconic Masters and Commander 2017 would indeed be nice targets for these! Thanks so much! :)

- Agetian
Agetian
Programmer
 
Posts: 3178
Joined: 14 Mar 2011, 05:58
Has thanked: 610 times
Been thanked: 415 times

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

Postby Marocksain » 19 Sep 2017, 14:42

I know it's not the patch area, but will anyone have the .txt from Ixacal?
Marocksain
 
Posts: 1
Joined: 19 Sep 2017, 14:14
Has thanked: 1 time
Been thanked: 0 time

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

Postby austinio7116 » 20 Sep 2017, 06:36

austinio7116
 
Posts: 180
Joined: 10 Mar 2017, 11:59
Has thanked: 20 times
Been thanked: 57 times

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

Postby austinio7116 » 20 Sep 2017, 08:36

austinio7116
 
Posts: 180
Joined: 10 Mar 2017, 11:59
Has thanked: 20 times
Been thanked: 57 times

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

Postby Bog Wraith » 21 Sep 2017, 00:31

Both sets are just great.

In Forge, I've always got the window sized for a card image of about 200 dpi, so with your 300 dpi up-sampled versions, the results in the smaller window size I use are nothing short of spectacular!

Thank you again for the time and work that you do to get these wonderful images available for us all here. It's very much appreciated.
'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: 1048
Joined: 28 May 2008, 22:40
Location: Shandalar
Has thanked: 347 times
Been thanked: 147 times

PreviousNext

Return to Pictures

Who is online

Users browsing this forum: Bing [Bot], Exabot [Bot] and 4 guests


Who is online

In total there are 6 users online :: 2 registered, 0 hidden and 4 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: Bing [Bot], Exabot [Bot] and 4 guests

Login Form