/cdn.vox-cdn.com/uploads/chorus_asset/file/24016885/STK093_Google_04.jpg)
/cdn.vox-cdn.com/uploads/chorus_asset/file/24808816/Starfield__The_Settled_Systems___Supra_Et_Ultra_____Starfield__The_Settled_Systems___Supra_Et_Ultra_2023_7_25_94252.263_1440p_streamshot.png)
Photoshop has been steadily adding AI-powered tools to its menus in recent years, but an incredible new demo from an independent research team shows where the best photo editors are going next.
DragGain may not be a fully fledged consumer product yet, but the research paper (picked up on Twitter by AI researchers @_empty And @icreatelife) shows the types of reality-warping photo manipulation that are going to be possible very soon. This AI-powered technology will re-challenge our definition of what a photo really is.
While we’ve seen similar photo editing effects before — especially in Photoshop tools like Perspective Warp — the DragGain demo takes the idea and user interface to a whole new level. As shown in the examples below, DragGain lets you precisely manipulate photos to change minor details like their subject’s expressions, body positions, and even reflections.
The results aren’t always perfect, but they’re impressive – and that’s because DragGain (the name is a portmanteau of ‘drag’ and ‘Generative Adversarial Network’) actually generates new pixels based on the surrounding context and where You put ‘drag’ points.
Photoshop’s Neural Filters, especially those available in the beta version of the app, have dabbled in similar effects for some time, for example by giving you sliders for ‘happy’ and ‘angry’ expressions. Can be tweaked. DXO software such as PhotoLab also has U Point technology which lets you point to the part of the photo on which you want to make a local adjustment.
But the power of the DragGain demo is that it combines both concepts in a pretty user-friendly way, allowing you to select the part of the photo you want to change and then your subject’s pose, expression, and more with very realistic results. can change completely.
When a refined version of this technology finally lands on smartphones, imperfect photos will be a thing of the past – as the idea of a photo will be a record of an actual moment in time captured.
DragGain also offers more granular control. If you don’t want to change the whole picture, you can apply a mask to a specific area – for example, your dog’s head – and the algorithm will only affect that selected area. That level of control should also help reduce artifacts and errors.
The research team also promised that in the near future it “plans to extend point-based editing to 3D generative models.” Until then, expect to see this kind of reality-warping photo editing popping up in some of the best Photoshop alternatives soon.
Analysis: The Next Photoshop-Style Revolution
These AI-powered photo editing tricks have echoes of Photoshop’s first early demo 35 years ago — and will likely have a similar level of impact culturally and on the democratization of photo editing.
In 1987, John Knoll, co-creator of Adobe Photoshop, took the photo above – one of the most important of the last century – on a Tahiti beach and used it to demonstrate the incredible tools that go into making the world’s most famous photo editing app. Will appear in ,
Now we’re seeing some equally important demos of image-manipulating tools, from Google’s Magic Eraser and Face Unblur to Photoshop’s new Remove tool, which lets you remove unwanted objects in your snaps.
But this DragGain demo, while only at the research paper stage, takes the whole concept of ‘photo retouching’ up a notch. It is improving the content of our photographs, rather than retouching them, using the original expression or as a starting point for something completely different.
Photographers might argue that this is more digital art than ‘drawing with light’ (the phrase that gives photography its name). But like the original Photoshop, these AI-powered tools will transform photography as we know it – whether we want to embrace them or not.
