Lots of interesting news has been coming from Google lately. They seem to be very devoted to the development of AI, and there is another novelty they may implement. Soon, Google could become able to remove the unwanted objects from your photos. In other words, if you take a photo through glass or a fence, the algorithm will automatically remove the obstruction and produce a clean photo.
We are all witnesses to vast technology advancement, and it’s fun to watch how it can be used for art. Artist Damien Henry seems to think so as well, so he wanted to see what happens when he uses machine learning to create a video – from a single image.
He used a prediction algorithm and gave it one photo at the beginning. From then on, the machine calculated each following frame and predicted what it would look like. The result is almost an hour long video composed of more than 100,000 frames, and it’s pretty impressive.
There are many ways and attempts to make the post-processing time shorter and more efficient. Researchers at Cornell and Adobe have teamed up and came up with a new solution. They have created a method that transfers the style of one image onto the other. It’s like a crossover between the Prisma app and copying and pasting settings in Lightroom.
With this solution, you are not supposed to edit the image and then copy and paste settings. You can transfer the style from a finished reference photo onto the one you want to enhance. This includes copying the time of day, lighting and weather from a reference image onto the one you’re editing.
Google has developed and launched a new encoder named Guetzli. It’s an open source algorithm that allows you to reduce the size of JPG files by up to 35% while keeping the quality unchanged. Additionally, you can increase the image quality while leaving the size unchanged.
Guetzli will allow you high compression density at a good quality of the image. It can be immensely helpful for saving images for the website. Using it will make the website use less data and thus be faster to load.
Despite how it may look, the above image is not a strange closeup of a Salvador Dali painting. No, it’s a bizarre creation created by a user of Russian web app Ostagram.[Read More…]
A team of researchers from MIT (Tianfan Xue, Michael Rubinstein, Ce Liu and William T. Freeman) are teaming up with Google with to present a new algorithm that is able to extract photographic inconveniences such as glares and reflections from photographs. The algorithm can then reproduce the image free of any reflections, in addition to being able to create an additional image of the reflection itself. This kind of problem solving would be especially useful when shooting behind glass or a fence, for example.[Read More…]
Last week, we wrote about how researchers at Brown developed a code that would allow realistic weather alterations in photo-editing through text commands. As fate would have it, the new trend these days is apparently groundbreaking algorithms. Two days ago, a video was uploaded showcasing Microsoft’s latest advancement in photography; using first-person-view cameras, researchers for the company developed an algorithm that makes what they call a hyperlapse. Watching the video, you’ll probably find yourself surprised by just how fluid everything almost looks. Keep reading after the break; seeing how it’s done is just as rewarding.
Do you ever notice how sophisticated and easily accessible futuristic technology can look at times when watching a movie? Just to throw an example out there, remember how subtly awesome it was when all Tony Stark needed to do to paint his armor was ask Jarvis to add some hot rod color? As advanced as technology is these days, Louis C.K. was right; we’re a bit spoiled when it comes down to how much we expect. Just the other night, I had a friend complaining that he was stuck on 4G because there wasn’t any LTE in the area.
The bottom line is that efficiency and speed both play a big role in how technology moves forward. As simple as it is to take your phone out and press a button to show the screen, we ended up finding a way to make pushing it unnecessary. As simple as it is to type in a password to buy an app, we replaced it with a fingerprint sensor. And as efficient as it is to Photoshop your pictures to change the weather, we’ve now found a way to let an algorithm do the job for us.