View previous topic :: View next topic |
Author |
Message |
piggsy
![Level 1 Level 1](rating1.gif) Joined: 04 May 2015 Posts: 84 Location: Brisbane, Australia
|
Posted: Tue Aug 02, 2016 3:48 am Post subject: waifu2x - deep convolution software for image resize/denoise |
|
|
piggsy wrote:
Just wanted to share this neat toy -
http://waifu2x.udp.jp/
it's kind of along the same lines as neural styles, deep dream, prisma, etc, which you may have heard of before. Only rather than repeatedly trying to match images to an artistic style over many iterations, this one tries to draw clean lines and (optionally) de-noise an image.
Probably best to use their own example image to show what it does -
as in its suggested use case it does a fantastic job of resizing compressed images of drawn art with lots of bold colours and strong lines. And it's really designed to hold up just for a goof image where you you have a bit of dvd or blu ray captured and want to make it visible at non-ant sizes. But if you start feeding it lossless images (or better, lossless unsharpened images) and keep on scaling, it can do some remarkable things.
Some examples -
100% - original image (1920x1200)
100% - 8x scaled image (15360x9600)
http://abload.de/img/dejesus100-8xlysgc.png
100% - original image (1151x1600)
100% - 8x scaled image (9208x12800)
http://abload.de/img/gorobo-100-8xvfurs.png
If you manage to find uncompressed sources of an image made of clearly defined lines you're pretty much only limited by memory requirements (much past ~10k x 15k pics do my 4GB 970GTX/16GB RAM box in). Although if you manage to de-jpg well enough to begin with you can push a jpg very far also, at least, probably far enough for most non-billboard purposes.
Here's how it handles a regular image of mine -
feed it the TIFF source (3411x2625)
100% - source
100% - 4x scaled output (13644x10500)
https://abload.de/img/clipboard01yvzgz.jpg
That's the simplest possible scaling too, without going in and doing anything differently noise or sharpening wise, just, asking it to blow it up. That's pretty neat.
Anyway, for most people who aren't prepared to install a linux, there's a web portal version of it at the link with a small-ish file output limit, and if you hit their github, you'll find a windows executable version of it with an installable GUI and right click "send to" menu support (look in waifu2x-converter_x64_1130\ExtendedSendTo) here:
https://github.com/tanakamura/waifu2x-converter-cpp
ed- just to add, this is one of the more lightweight neural network photography things going - even if you don't have a CUDA or OpenCL/GCN supported GPU, you can still make very big images in reasonable timeframes on the CPU only. About 15-40 minutes depending on the source and output on my Haswell/DC I5 at 4.3ghz, vs about 0.5/1 minute on the 970. _________________ https://www.flickr.com/photos/piggsyface/
You can't fax glitter. |
|
Back to top |
|
![](templates/mflenses/images/spacer.gif) |
kds315*
![Level 4 Level 4](rating4.gif) Joined: 12 Mar 2008 Posts: 16619 Location: Weinheim, Germany
Expire: 2021-03-09
|
Posted: Tue Aug 02, 2016 6:12 am Post subject: |
|
|
kds315* wrote:
![Like 1 small](images/smiles/like-1s.gif) _________________ Klaus - Admin
"S'il vient a point, me souviendra" [Thomas Bohier (1460-1523)]
http://www.macrolenses.de for macro and special lens info
http://www.pbase.com/kds315/uv_photos for UV Images and lens/filter info
https://www.flickr.com/photos/kds315/albums my albums using various lenses
http://photographyoftheinvisibleworld.blogspot.com/ my UV BLOG
http://www.travelmeetsfood.com/blog Food + Travel BLOG
https://galeriafotografia.com Architecture + Drone photography
Currently most FAV lens(es):
X80QF f3.2/80mm
Hypergon f11/26mm
ELCAN UV f5.6/52mm
Zeiss UV-Planar f4/60mm
Zeiss UV-Planar f2/62mm
Lomo Уфар-12 f2.5/41mm
Lomo Зуфар-2 f4.0/350mm
Lomo ZIKAR-1A f1.2/100mm
Nikon UV Nikkor f4.5/105mm
Zeiss UV-Sonnar f4.3/105mm
CERCO UV-VIS-NIR f1.8/45mm
CERCO UV-VIS-NIR f4.1/94mm
CERCO UV-VIS-NIR f2.8/100mm
Steinheil Quarzobjektiv f1.8/50mm
Pentax Quartz Takumar f3.5/85mm
Carl Zeiss Jena UV-Objektiv f4/60mm
NYE OPTICAL Lyman-Alpha II f1.1/90mm
NYE OPTICAL Lyman-Alpha I f2.8/200mm
COASTAL OPTICS f4/60mm UV-VIS-IR Apo
COASTAL OPTICS f4.5/105mm UV-Micro-Apo
Pentax Ultra-Achromatic Takumar f4.5/85mm
Pentax Ultra-Achromatic Takumar f5.6/300mm
Rodenstock UV-Rodagon f5.6/60mm + 105mm + 150mm
|
|
Back to top |
|
![](templates/mflenses/images/spacer.gif) |
piggsy
![Level 1 Level 1](rating1.gif) Joined: 04 May 2015 Posts: 84 Location: Brisbane, Australia
|
Posted: Wed Aug 03, 2016 12:58 am Post subject: Re: waifu2x - deep convolution software for image resize/den |
|
|
piggsy wrote:
One other thing that makes this handy - other than just being able to enlarge a lot of image types - is what happens when you combine this with other neural net programs.
The fastest one I know of right now is Prisma -
http://prisma-ai.com/
which is an ios/android cloud app that, while it doesn't let you use custom style files, has more or less enough of them to have fun in their kit, and it lets you fine tune the effect strength instantly. Most others involve installing a bunch of packages in linux, several minutes of waiting, and often have pretty poor output sizes without a lot of VRAM to throw at them (about 800-900px square was about all I could get out of my 970).
Prisma is kind of crappy output wise, unfortunately - it works good enough for your phone and for a goof, but it's hard to get something like a "serious" image out of it - about 1080px square and 80% quality jpg is all it will spit out. Fortunately you aren't also just limited to your smartphone's camera, you can upload any file sent over USB or on a smart card also. Here's just a random photo sent through it -
Pretty cool effect. But on closer inspection you can see how bad it is at a low level -
here's what waifu2x does to that at 8x scaling and 2 factor noise reduction -
https://abload.de/img/cleanoutukqrv.jpg
pretty neat huh. Full size -
https://abload.de/img/78ab87e7a3df0bc4742b6czssg.jpg
Some others - prisma app out, original file sent to prisma, waifu2x'd output at 8x_N2. I should also mention, I'm just using 8x to show how ridiculous an enlargement factor you can use and how good it will still look given a crappy jpg that was already a "neural net done quick" fast/low quality image, there's no reason to go to a 55mb png at 8000px size if 2x would satisfy your output requirement.
https://abload.de/img/pa010082thituoj.jpg
https://abload.de/img/1dd66cd063887318e467cbzss2.jpg
https://abload.de/img/p1290136raung.jpg
https://abload.de/img/2e5137f7371faccc574d521s2m.jpg
https://abload.de/img/p1280097th7fuh6.jpg
https://abload.de/img/111111111111111111111ncs9e.jpg
https://abload.de/img/p1180227t82u0g.jpg
https://abload.de/img/111111111111111111111f8sv1.jpg
https://abload.de/img/p4140014tht8uix.jpg
https://abload.de/img/111111111111111111111q3s03.jpg
https://abload.de/img/p4100124thpfsm7.jpg
https://abload.de/img/b7b9d7335e4bf67ad0c351bsdu.jpg
https://abload.de/img/p9280101th2lukt.jpg
https://abload.de/img/ff333dea9152b0979c55ciisw1.jpg _________________ https://www.flickr.com/photos/piggsyface/
You can't fax glitter. |
|
Back to top |
|
![](templates/mflenses/images/spacer.gif) |
bghomofaber
![Level 1 Level 1](rating1.gif) Joined: 03 Mar 2016 Posts: 154
|
Posted: Fri Dec 30, 2016 1:30 pm Post subject: |
|
|
bghomofaber wrote:
For many deconvolution, sharpening and a myriad other cool filters (including film emulation) I use g'mic filter packs with gime experimental from partha.com (both as appimage for linux and for windows).
For deconvolution and resize I also use Michael's Winter Image Analyzer from meesoft.dk.
I will surely try the suggested program, ty for posting |
|
Back to top |
|
![](templates/mflenses/images/spacer.gif) |
bghomofaber
![Level 1 Level 1](rating1.gif) Joined: 03 Mar 2016 Posts: 154
|
Posted: Fri Dec 30, 2016 1:34 pm Post subject: |
|
|
bghomofaber wrote:
Will also post my linux (fedora) compilatione xperience from the github software
https://github.com/nagadomi/waifu2x
my guess is that it will be a good battle ... |
|
Back to top |
|
![](templates/mflenses/images/spacer.gif) |
piggsy
![Level 1 Level 1](rating1.gif) Joined: 04 May 2015 Posts: 84 Location: Brisbane, Australia
|
Posted: Mon Jan 02, 2017 8:40 am Post subject: |
|
|
piggsy wrote:
bghomofaber wrote: |
For many deconvolution, sharpening and a myriad other cool filters (including film emulation) I use g'mic filter packs with gime experimental from partha.com (both as appimage for linux and for windows).
For deconvolution and resize I also use Michael's Winter Image Analyzer from meesoft.dk.
I will surely try the suggested program, ty for posting |
It's "deep" rather than "de"-convolutional, as in the style of neural network it's using - one with stacked layers. _________________ https://www.flickr.com/photos/piggsyface/
You can't fax glitter. |
|
Back to top |
|
![](templates/mflenses/images/spacer.gif) |
|
|
You cannot post new topics in this forum You cannot reply to topics in this forum You cannot edit your posts in this forum You cannot delete your posts in this forum You cannot vote in polls in this forum
|