You know how in CSI, the cops always try to "enhance" a shot to zoom in and read (non-existent) details in photos? It's amusing to the rest of us, but perhaps one day won't be all that impossible, with artificial intelligence.
Researchers have been adopting neural networks and machine learning technologies to help computers fill in missing detail in photos.
Some consumer-ready websites are already making some of this magic accessible to you and me.
SEE ALSO:Photographer dangles models off a 30-storey skyscraper for a Nike shootOne of these is called Let's Enhance, which was recently launched with an easy drag-and-drop interface.
After you let its system process your picture, you'll be able to download a shot that's been enlarged by four times, by clicking the "magic" option.
The results are certainly impressive. We compared it with several small pictures that were enlarged with a basic Photoshop interpolation method.
Left:Manually enlargedjack russel puppy on white carpet; Shutterstock ID 519357004Credit: Shutterstock / SmitRight:Let's Enhance version
Left:Manually enlargedHands of an elderly woman holding the hand of a younger woman. Lots of texture and character in the old ladies hands.; Shutterstock ID 110911754Credit: Shutterstock / Richard LyonsRight:Let's Enhance versionLooking at this shot of people's hands, Let's Enhance has restored the wrinkles in the texture of the hand in the foreground.
It may have been a little too enthusiastic with this, producing fairly harsh outlines, but it's certainly reproduced the original picture quite faithfully.
Left:Manually enlargedCute cat lying on his back on the carpet. Breed British mackerel with yellow eyes and a bushy mustache. Close up.; Shutterstock ID 572338033Credit: Shutterstock / GreenArtRight:Let's Enhance versionAnd if you look at the cat above, you can see the jagged lines around its eyeballs, where basic interpolation has simply filled in the missing pixels by copying the ones around them.
Let's Enhance's version has restored the smoothness of the lines, and even reproduced the reflection of the photographer in the blacks of the cat's eyes.
Founders Alex Savsunenko and Vladislav Pranskevičius, told PetaPixeltheir system rolls in machine learning frameworks such as SRGAN and EDSR to upscale small images.
SRGAN, for example, relies on a generative adversarial network, which basically pits two neural networks against each other to test and fine-tune an image repeatedly.
Looks like some of our TV magic is coming to the real world one day. Enhance!
Via GiphyFeatured Video For You
Is the iPhone X's facial recognition twin compatible?
TopicsArtificial IntelligencePhotoshop
张永久
刘转亮
巫慧敏
