Read the full blog entry here.
Pixelmator Pro update improves ML Super Resolution and ML Denoise
2020-02-11 14:10:01
Howdy! Pixelmator Pro 1.5.5 has just been released and it brings some significant improvements to ML Super Resolution and ML Denoise as well as two new Automator actions for those two features. Because seeing is believing, we thought we’d whip up a blog post with some examples to highlight the changes.
Read the full blog entry here.
Read the full blog entry here.
0
2020-02-11 16:46:27
Fantastic update! Are you working on something that comes closer to Topaz's approach? Why is the Automator action limited to 3x increase? Can I input the values manually?
0
2020-02-12 08:44:48
Closer in what way? As far as we've seen, their approach doesn't provide real-time (or close to real-time) feedback and that's what we'd be aiming for.
As for 3x — that's the most computationally efficient amount and that's how much the underlying algorithm increases every image, even if you choose a smaller size in the Image Size dialog. We simply reduce the result to the required size afterward using the Bilinear algorithm so you can use the Scale Images action to scale the image down. If you choose more than 3x, the algorithm runs twice, so you can simply apply the Increase Resolution of Images action twice to get the same result (and then use the Scale Images action to get an exact size).
0
2020-02-14 08:45:49
Great update. Nice to see improvements and bug fixes as well as Automator actions. The Denoise does a good job now. Hopefully the edges and contrast could be improved but really good job.
0
2020-02-17 10:27:44
Ah I understand. Yes their approach is very far away from being realtime. That's true. But what I meant was the way new texture is generated. I don't know how they do it but maybe you have the answer.2020-02-12 08:44:48
Closer in what way? As far as we've seen, their approach doesn't provide real-time (or close to real-time) feedback and that's what we'd be aiming for.
As for 3x — that's the most computationally efficient amount and that's how much the underlying algorithm increases every image, even if you choose a smaller size in the Image Size dialog. We simply reduce the result to the required size afterward using the Bilinear algorithm so you can use the Scale Images action to scale the image down. If you choose more than 3x, the algorithm runs twice, so you can simply apply the Increase Resolution of Images action twice to get the same result (and then use the Scale Images action to get an exact size).
Would love to see this kind of batch processing inside of Pixelmator Pro to see an actual progress bar or something like that.
0
2020-02-17 13:55:23
We can't know for sure what kind of approach they took but it doesn't really matter all that much — we plan to keep improving our algorithms (not just for ML Denoise) regardless. And if you ever find any images where you think we could do better (either generally, or compared with other apps), sharing one or two samples with us at support@pixelmator.com helps us a lot!2020-02-17 10:27:44
Ah I understand. Yes their approach is very far away from being realtime. That's true. But what I meant was the way new texture is generated. I don't know how they do it but maybe you have the answer.
Would love to see this kind of batch processing inside of Pixelmator Pro to see an actual progress bar or something like that.
As for batch processing inside the app, a more refined photo-centric workflow sounds like something we should consider if/when we bring Pixelmator Photo to macOS. I think there's a lot of potential to do something very cool with it.
0
2020-02-20 13:41:06
I must admit it´s fantastic! I upscaled a lot of footage so far and the results are stunning. WOW!!!
0
2020-05-16 09:20:03
I wonder what is the purpose of increasing the pixel size and dpi following image transformation using ML Super Resolution? Can't it be achieved on the image with the same pixel size?
0
2020-05-18 11:42:54
Sometimes, though not usually. If the image is quite small, the amount of detail in it is constrained the number of pixels. For example, if there is a face represented by, say, 48 total pixels (8 x 6), you can't make the edges more natural without adding more pixels to the image, it's physically impossible. If the image is larger and the face is represented by, say, 192 pixels (16 x 12) but it's blocky or blurry because someone previously upsampled it using nearest neighbor/bilinear, then it would theoretically be possible to increase detail while using the same number of pixels, but that would require a different approach. In a case like that, the ML algorithm would probably need to be trained to recognize previously upsampled images and detect the resampling algorithm used in order to undo those changes and then, while keeping the same size, upsample the image again. Also, this isn't a very common problem — usually, the images are just very small, so the pixel size needs to be increased to physically be able to create natural edges and reintroduce detail.
0