Skip to main content

Don’t like the weather for your photo shoot? Change it later with this algorithm

How often has bad weather or the wrong season stopped you from heading out and taking pictures? Have you ever had to wait for a specific season to arrive so you could realize a specific photo project you had in mind? Do you sometimes wish you could browse your photo collection by specific ambient values such as sunshine, clouds, rain, or a particular season? Soon, all these concerns will no longer be an issue, thanks to a new algorithm developed by Brown University researchers.

At the SIGGRAPH 2014 conference on computer graphics and interactive techniques, the researches first presented their algorithm (see the video above) which can be used to do multiple things, including browsing photos by weather tags and altering the weather or seasonal appearance in a picture. By tagging photos with ambient values such as “rain,” “clouds,” “sunny,” “autumn,” etc., the algorithm is able to learn about the specific visual properties of weather conditions, seasons, or moods associated with certain ambient values.

By creating a large database of photos tagged with a set of ambient values, the researchers trained their algorithm not only to select individual pictures with a specific ambient appearance from a photo collection, but also to replicate certain weather conditions in pictures that have been taken at entirely different conditions. For example, the algorithm is able to make a photo taken during a warm summer day look like it was taken in winter or fall, or introduce rainfall or even the appearance of nighttime into a picture taken in broad daylight.

Related: Learn why polarizer filters are useful, and how to use them

Currently, the algorithm is still under development, but the research team hopes to have a consumer version of the program soon. According to James Hays, assistant professor of Computer Science at Brown University, the goal of the project is to “make image editing easier for non-experts” – that is, casual hobby photographers that aren’t familiar with all the secrets of Photoshop and other professional editing tools.

While the results generated by the algorithm still look a bit crude, there’s hope that the more images will be fed into the database, the more accurately the algorithm will be able to replicate certain weather conditions in photography. Also, as research progresses, changes may be made to how the algorithm applies ambient values to photos in order to make the results look more realistic.

So, does this mean that in the future, we can take a picture at any time of day and our computers will make them look the way we want them? Probably not, at least not too soon. After all, there are limitations as to what the algorithm can do. Where there’s no sunlight or green foliage to begin with, it’s rather difficult to add these things to a picture. But for simple edits to a picture’s appearance, the algorithm developed at Brown University seems to be rather capable already.

(h/t PetaPixel)

Felix Esser
Felix is a freelance tech journalist with a strong focus on photography. Based out of central Germany, he contributes to…
How to transfer photos from an iPhone to a computer
The Apple iPhone 15 Plus's gallery app.

As the old saying goes, the best camera is the one you always have with you. If you're like most iPhone users, that means you've likely amassed a sizeable collection of photos on your device. However, while Apple's Photos app is a great way to manage and view your photo library, it's never a good idea to keep all your eggs in one basket. After all, suffering a lost or broken iPhone is painful enough without also losing all your precious digital memories in the process.

Even if you're backing up your iPhone to iCloud or your computer, it's a good idea to keep your photos backed up separately. After all, opening a folder or a photo management app is a much easier way to get at your photos than trying to extract them from an iCloud or iTunes/Finder backup, which requires either restoring them to another iPhone or relying on special software tools.

Read more
This Canon mirrorless camera deal cuts the price by $85
A Canon EOS R100 mirrorless camera on a white background.

For one of the best camera deals, check out the discount on the Canon EOS R100 mirrorless camera over at Walmart right now. Usually you’d have to pay $499 for the camera, but right now you can buy it for just $414, meaning you’re saving $85 off the regular price. The perfect time to treat yourself to a superior photography experience for less, here’s what you need to know before you commit to a purchase.

Why you should buy the Canon EOS R100 Mirrorless Camera
Ideal for anyone checking out the best mirrorless cameras but wanting to keep costs down, there’s a lot to love about the Canon EOS R100 Mirrorless Camera. It’s the smallest and lightest EOS R series camera while packing in plenty of features. It has excellent still-image capabilities with its 24.1 Megapixel APS-C size CMOS image sensor and DIGIC 8 processor. It also has Dual Pixel CMOS AF with the ability to detect human faces and focus on their eyes. Its sensor is significantly larger in size than many smartphones and can capture images with natural bokeh. It’s also able to take high-sensitivity and low-noise images which capture the atmosphere, even if you’re taking photos in low-light conditions.

Read more
Can a $500 Pixel phone beat a $1,000 iPhone in a camera test? I found out
iPhone 15 Pro (left) and Google Pixel 8a camera modules.

Right before Google I/O 2024, Google showed off the latest Pixel device, the Google Pixel 8a. This is the latest offering from the Pixel A-series, which is a more budget-friendly Pixel for those who don’t need all the bells and whistles of the flagship Pixel 8 or 8 Pro.

The Pixel 8a features a new design with more rounded corners and a matte-finish back. It packs Google’s latest silicon, the Tensor G3, but the camera hardware remains unchanged from its predecessor, the Pixel 7a.

Read more