Welcome to Doom9's Forum, THE in-place to be for everyone interested in DVD conversion. Before you start posting please read the forum rules. By posting to this forum you agree to abide by the rules. |
24th July 2023, 08:21 | #1 | Link | |
Registered User
Join Date: Aug 2002
Location: Italy
Posts: 312
|
Mathematically Evaluating mpv's Upscaling Algorithms
Just discovered this - updated - study of performance and quality by João Vitor Chrisóstomo:
https://artoriuz.github.io/blog/mpv_upscaling.html Quote:
__________________
Hybrid Multimedia Production Suite will be a platform-indipendent open source suite for advanced audio/video contents production. Official git: https://www.forart.it/HyMPS/ |
|
24th July 2023, 11:42 | #2 | Link |
Registered User
Join Date: Jun 2020
Posts: 303
|
You probably should mention that the test results you posted are for an Anime test image.
While the linked study is Anime focused it also tests a live action photo, with different results. It's worth a look for those who haven't done so already.
__________________
bShaders: realtime Effects/filters for video players |
16th February 2024, 22:00 | #5 | Link |
Registered User
Join Date: Oct 2018
Posts: 336
|
The ArtCNN models have been trained with the Manga109 dataset, this is a huge advantage when testing with anime content, in short, it is what makes the biggest difference, so their good results are not surprising at all. Also, not everyone knows that FSRCNNX has been trained with increased distortion, which makes it able to reduce compression artifacts, but also makes it a bit less sharp with clean content.
I'm not really into this anymore to make a more scientific comparison, I'll leave it to whoever may be interested, but looking at the network architecture, my bet is that the results of these models should be very similar to the AiUpscale LineArt models, which can be used also in mpv. These models work really well for 2x (or maybe even 3x) upscaling, the real challenge is for 4x upscaling, where GAN models have shown great superiority, but are too resource intensive to be used in real time.
__________________
AviSynth AiUpscale Last edited by Alexkral; 16th February 2024 at 22:03. |
17th February 2024, 06:06 | #6 | Link |
Registered User
Join Date: Oct 2012
Posts: 8,152
|
ArtCNN is trained like this:
The shaders are trained on the Manga109 dataset using the Adam optimiser with a learning rate of 1e-4 and the L1/MAE loss function. The high-resolution images are downsampled with a box filter, and they're also split into small 64x64 patches for performance and memory reasons. and what is used in that test: magick convert aoko.png -colorspace rgb -filter box -resize 50% -colorspace srgb downsampled.png shocker. it has to be trained on something so fine. i'm not going into the sRGB part... let's take and anime image and look at it. gpu-next has been avoided because of a current bug that's been around for awhile. FSRCNNX_x2_16 ArtCNN_C4F32 and NGU sharp very high i'm not going to tell which is which because they all perform terrible to whatever on this image: https://slow.pics/c/8jsbuzNR please guess what is what. edit: more scaler this time with names https://slow.pics/c/UoS7hM07 this is one image so no need to jump to a general conclusion here. ArtCNN is quite impressive compared to NGU sharp and fsrcnnx because they both need to cease and desist here. the problem on this image is ArtCNN looks the same as super xbr or well it looks the same but rings... super xbr biggest problem is it is quite unremarkable and well rings. what so ever ArtCNN not going completely crazy yet is very good achievement anime 4k was added for comedic effect. Last edited by huhn; 17th February 2024 at 10:34. |
Tags |
mpv, player, software, study, upscale |
Thread Tools | Search this Thread |
Display Modes | |
|
|