Hacking Photography - one Picture at a time
Creating a 3D model of someone’s face usually requires multiple shots taken from different angles. But researchers from the University of Nottingham and Kingston University have created an AI tool that makes it from a single portrait photo.
The scientists describe the 3D face reconstruction as a “problem of extraordinary difficulty.” However, they’ve managed to use neural networks to turn any 2D portrait into a 3D model. There’s also a free online demo for you to try it yourself.
Google’s recent research has shown that an algorithm can easily remove watermarks automatically, making the images vulnerable to unauthorized use. In their latest paper, they present the solution that should help photographers and stock photo websites increase the watermark protection.
Photo enhancing apps have come a long way over the past few years. However, researchers from MIT have worked with Google and have gone a step further: they are introducing an app able to retouch your photos before you even take them.
They use deep learning to create the software. When you turn the app on, it enhances your images in real time, and you can see the expected outcome on the display before you snap a photo. It’s able to retouch the images in different styles, and it should be small enough not to be laggy on a mobile device.
I remember how excited I was when I first started posting on instagram. I finally had a platform to get my work seen, tell my stories, share my life and get inspired by those of others. It was all about creativity and art and The Work, it was fair and ethical and just awesome!
Things have changed a lot since, and now I often find myself feeling sick to my stomach when I have to post a new picture!
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…]
You can find out more about John on his website or follow him on Facebook and YouTube.
can change a lens mid-rappel, swap a memory card while treading water, or use a camel as a light stand.
To see more of his work please visit his studio website blurMEDIAphotography, or follow him on Twitter, 500px, Google Plus or YouTube.
JP’s photography is available for licensing at Stocksy United.
Find my work on My website or follow me on Facebook or My page
