by Brandon Butler
Adobe shows off new Super Resolution machine learning in Adobe Camera Raw 3/12/2021

Jaron Schneider with PetaPixel:

In addition to adding support for the lastest Apple Mac products, Adobe also has unveiled what it is calling “Super Resolution.” Super Resolution is a new feature to Adobe Camera Raw that uses machine learning technology to boost the resolution of an image, resulting in “higher quality results than ever before.” […]

“Imagine turning a 10-megapixel photo into a 40-megapixel photo,” [Adobe’s Eric] Chan says. “Imagine upsizing an old photo taken with a low-res camera for a large print. Imagine having an advanced ‘digital zoom’ feature to enlarge your subject.”

If you have Pixelmator Pro, you already have a feature like this. I’ve used it a few times to upsize some digital artwork I’ve created on my iPad Pro that was just a little too low resolution for me to print at the quality I wanted: resizing with ML Super Resolution was as simple as entering in a new resolution, clicking the radio button for MLSR, and clicking OK. And wow, is it fast in Pixelmator on an M1 MacBook Air. The details are sharp and nothing about the end result looks digitally upsized — at least to my eyes, and I’m the one that created the original artwork!

Now I’ve never used ML Super Resolution on a photo, but if I needed to add a few inches to a photo I wanted to print, I wouldn’t hesitate to process it with MlSR first. This isn’t your grandfather’s bicubic resampling.

Adobe is also sharing news of their re-write of Photoshop for M1 Macs:

“While we will continue to work together with Apple to further optimize performance over time, we are very happy with the results so far. We think our customers using these new Macs will love the difference, too. Don’t blink. You might miss the splash screen launching…” Adobe says.