Skip to main content

Photolemur is an automatic image editor that gets better over time

photolemur ai image editing screenshot 3
Image used with permission by copyright holder
Artificial intelligence (AI) is all the rage in photo editing these days. While some in-development tools promise a future of near-magical image generation, Photolemur takes a more realistic approach. The MacOS app, currently in beta, uses AI to apply a number of automatic image enhancements based on the content of an image. It’s a one-click, no-nonsense solution for people who want to spice up their images without putting in hours of work.

According to its website, Photolemur is powered by an algorithm that took years to develop. It performs a complex analysis of each image it’s fed, processing millions of pixels per second. It can detect faces and other objects, and performs adjustments accordingly. The app can do anything from straightening horizons to removing haze to significantly enhancing skies, depending on what’s needed. This process happens quickly and automatically, with the only user-controllable option being a slider at the bottom of the screen with “Realistic” on one end and “Vivid” on the other.

photolemur-screenshot-2
Image used with permission by copyright holder

Photolemur is built on twelve discrete technologies for enhancing different aspects of a photo. These include color recovery, sky enhancement, exposure compensation, smart dehaze, natural light correction, foliage enhancement, tint perfection, JPEG fix, horizon straightening, and RAW processing. The two remaining features, noise reduction and face retouching, aren’t currently turned on in the beta.

We’ve spent some time with the beta, and our results have been a little hit and miss. As the company clarified in an email, the app definitely works better with RAW files than JPEGs, although the quality of its results also seems dependent on the type of photo. High-dynamic range scenes, like landscapes with bright skies and dark foregrounds, can suffer from excessive shadow brightening. “Halos” can also appear around high-contrast edges. In practice, moving the slider toward the “Realistic” side helped alleviate these issues.

On the other hand, we found Photolemur did a good job at more modest adjustments, including white balance, exposure correction, and improving the color and brightness of foliage.

It’s difficult to judge Photolemur in its current state, as it is designed to grow more accurate over time. Users will “train” the algorithm every time they load an image. Pictures that are saved or shared are added to a “success” database, while those that are not are added to a “blacklist.” The app then bases future enhancements off of patterns of previous successes.

The user interface is incredibly clean and simple, but does include support for batch processing (currently limited to 20 photos at a time, but this will be increased for the full version). It’s certainly not the right program for photographers who want to have a high degree of control over their edits, but it is well suited for casual users. We’d like to see a mobile version of the app in the future, as that would seem to be more in line with the type of simple and automatic editing Photolemur is geared for.

If you’re interested in trying out Photolemur for yourself, you can download the free beta (MacOS only) now.

Editors' Recommendations

Daven Mathies
Former Digital Trends Contributor
Daven is a contributing writer to the photography section. He has been with Digital Trends since 2016 and has been writing…
The house appraiser of the future is probably an A.I. algorithm
use infrared thermometer easily spot heat leaks house thermal view

To paraphrase 1984’s The Terminator, the artificial intelligence developed by residential real estate company HouseCanary will absolutely not stop, ever, until your house is properly valued.

The robot appraiser takes advantage of new federal regulations raising the threshold value of homes exempt from human evaluation. In doing so, it’s allowed to do a job that once required a flesh-and-blood human to perform. Namely, it will determine the current value of a property by inspecting its exterior condition and amenities.

Read more
Photorealistic A.I. tool can fill in gaps in images, including faces
pen net image infilling screen shot 2019 07 16 at 05 19 53

You only need to go check out the latest Hollywood blockbuster or pick up a new AAA game title to be reminded that computer graphics can be used to create some dazzling otherworldly images when called for. But some of the most impressive examples of machine-generated images aren’t necessarily alien landscapes or giant monsters, they’re image modifications that we don’t even notice.

That’s the case with a new A.I. demonstration created by computer scientists in China. A collaboration between Sun Yat-sen University in Guangzhou and Beijing’s Microsoft Research lab, they’ve developed a smart artificial intelligence which can be used to accurately fill in blank areas in an image: Whether that’s a missing face or the front of a building.

Read more
What’s that liquid? IBM’s flavor-identifying ‘e-tongue’ will tell you
ibm e tongue project 48055705116 bdaf7b65de o

IBM Hypertaste: An AI-assisted e-tongue for fast and portable fingerprinting of complex liquids

With its Watson technology, IBM has helped create a pretty convincing artificial brain. But now it’s seemingly ready to move onto other body parts as well -- and it’s settled on the tongue as a next step. As developed by computer scientists at IBM Research, the A.I.-assisted e-tongue is a portable device, equipped with special sensors, that allow it to taste and identify different liquids.

Read more