Researchers at the University of Washington have developed a deep learning method that only needs a single photo to make a believable video. If you have a photo of a waterfall, a river, smoke, or clouds, it predicts the previous and the next frame and creates a pretty cool animation.
Computational vs. traditional photography — Complementary, not contradictory
by Leave a Comment
There are now two ways of creating digital images with a camera. You can either follow a software-centric computational photography approach. The other way is to stick to traditional hardware-centric optical photography. The former is used with AI to help enhance the final image, the latter relies on the quality of the camera’s components (e.g. lens, sensor). The two techniques may differ, but they are not at all on a collision course. They can complement each other and even address each technique’s limitations.
Instagram finally reveals more about how its algorithm works
by 4 Comments
The Instagram algorithm is something many of us love to hate. It’s an invisible entity we’ve been trying to beat over and over again to make our content more visible. But the truth is – none of us really know how exactly the algorithm works. Well, the company has finally decided to become more transparent about it and tell us more about how Instagram picks content for its users.
Google will now pay for your photos, although only $0.20 a pop
by 24 Comments
Remember that Google wanted you to help train its photo algorithm for free? Well, now you can actually do it for cash. Google has launched an app called Task Mate, and it allows you to get paid for doing simple tasks such as taking photos, recording voice clips, and more.
Google Photos wants you to train its algorithm for free
by 2 Comments
If you’ve ever wanted to work for Google, now’s your chance. Well, sort of. Google Photos is now expanding its survey that helps the algorithm recognize what’s in the photos. In other words, you’ll be able to label your images from scratch and tag them in order to train Google’s algorithm further.
This AI turns rough sketches into portraits
by Leave a Comment
Artificial intelligence keeps getting better. A group of scientists from China has developed an algorithm that can turn sketches into realistic portraits. It even works with pretty rough sketches, and the end results look very close to real photos of people.
This AI turns pixelated faces into real portraits, but not without hiccups
by 3 Comments
We’ve already seen some AI software that can upsample low-res images. You know, CSI-style. Face Depixelizer is another AI-powered software, particularly focused on faces. It can take a pixelated, low-res photo and turn it into a realistic portrait. While the results are pretty impressive – the app doesn’t come without its quirks.
Instagram now lets you see the accounts that appear in your feed most and least
by 1 Comment
Instagram has introduced a new feature that could give us a glimpse of why we see some accounts in our feed more and some less often. Introduced on Thursday, the feature lets you see which accounts are shown in your Feed the most, and with which accounts you’ve had the least interaction.
This algorithm removes water from underwater photos, and they look incredible
by 14 Comments
Oceanographer and engineer Derya Akkaynak from MIT has developed an algorithm that “removes water” from underwater images. As a result, it makes the underwater world look exactly as it would if we were to see it on dry land. And it’s not only useful for scientists. For us “common folks,” it’s amazing to see the underwater world in a completely new context.
Scientists develop an algorithm that recovers detail in your blurry photos
by 7 Comments
A group of MIT researchers has come up with a way to recover lost details from your blurry images and even videos. They have developed an algorithm that recognizes and automatically recovers blurred parts in your videos and stills.
- 1
- 2
- 3
- 4
- Next Page »
FIND THIS INTERESTING? SHARE IT WITH YOUR FRIENDS!