I Didn’t Believe the Hype Until I Tried AI Noise Reduction Myself

As a landscape photographer, I generally don’t deal with too much noise in my images, unless I’m shooting nightscapes. Once I started photographing more wildlife during my time in Alaska, I decided to give it a try and was absolutely blown away by the results. As a newbie to wildlife photography, which involves shooting in the exact opposite style of landscape photography, there was a lot to learn. One of those lessons was that I had to increase my ISO to heartbreaking levels, at least by my standards which usually include never going above ISO 400. After capturing a few shots around ISO 5000 and then pushing all the way up to ISO 12,800, I felt it was time to try one of the plethora of software options I continually get advertised for to see if they could do anything close to what they advertised.

Throughout this article and video, I will be using ON1 NoNoise AI, but I fully suggest that you try all the available options to find what gives you the best results. Many of them have free trials and you can test them out at your leisure.

Nightscape noise reduction

I’ve previously tried reducing noise in a few nightscape images I’ve taken over the years and had mixed results. Sometimes it gave me decent results and other times it didn’t do much at all. I ran a recent nightscape image I took in Oregon through ON1’s NoNoise AI with decent results. Whatever software you use, they usually suggest that you process your images through the program as raw files, rather than after you’ve finished editing them. I had already completed this image which involved a milky way stacked with 20 stars mixed in with a 3 minute exposure for the foreground, so I wasn’t providing the best possible file to the program, but it still did a great job.

Above is a close-up of the noise reduction before and after. The obvious difference is the amount of noise removed from dark areas, but it’s important to pay attention to the detail put back into those areas. Also notice how beautiful the water is without reducing the ethereal feel of this three-minute exhibit. If this smoothing is too much for you, you can always adjust the amounts applied or be precise and mask certain areas.

Here’s the final full before and after image, keep in mind that the starry area has been stacked in both images, which means there isn’t much noise to remove. What was good was that the processing didn’t remove detail in the milky way and starry areas. Overall I was very happy with the results, but I wasn’t blown away…until I started processing some wildlife photos I took.

mind blown

Unlike the previous image, my workflow for these images involved first running ON1’s NoNoise AI and then applying my changes, which should yield better results than doing it in reverse .

The image above was taken at ISO 12,800 and while the uncropped version would have been passable for online use, as soon as I cropped the eagle the Canon R5 noise became much more apparent. That’s when I tried to process it through the software and was literally blown away. Not only did it reduce noise very well, but it also added and improved detail in a subtle yet realistic way. Pay attention to the definition of the eagle’s feathers throughout the image, both brown and white. In my eyes, this not only reduced the grainy texture of the noise, but also provided a shiny texture in the feathers that wasn’t there before. Just like before, also notice the water, how it retains the definition of the ripples without removing detail while completely removing noise.

I took this image a few weeks ago and posted it to Instagram with no noise reduction added outside of Lightroom’s built-in noise reduction. Even at small resolutions I noticed the noise specifically in the out of focus areas of the trees and basically wrote this image as unusable because of it. Although it was shot at ISO 5000, I had to recover quite a bit of shadow detail and overall those out of focus areas were distractingly noisy.

At almost 100% harvest it becomes quite apparent how amazing the results are and to me it feels like magic. The feathers, the beak, the blurry areas – everything in the image looks better after processing it through the software. Look specifically at the areas where there are fuzzy leaves in front of the eagle and how the transition area from those fuzzy leaves to the eagle feathers has a lot of green in it, as you would expect with fuzzy leaves. Then take a look at the noise-reduced version and how it retained the essence of those fuzzy green parts while still reducing the noise properly. Typically noise comes in the form of a green or red grainy texture and the fact that it can tell the difference between noise and actual image detail is amazing.

If your results aren’t as good, I suggest adjusting the amounts of processing you apply to your image. The truth is, I don’t think I changed a single setting on most of these images. You can find more examples in the video in this article.

Conclusion

Years ago when I tried software like this it always gave very mixed results and ended up ruining parts of the image like the transitions from the branches to the background. Since the addition of learning-based computing, the AI ​​part of all recent software suites, the results have become incredibly powerful. Especially when it comes to wildlife. When the software can detect what type of object, in this case a bird, is in the image. It enhances image areas even better after removing noise.

Nightscape results are good, but are limited by trying to guess and assess every object and detail in the image. Overall I’m very pleased with the results and it means I can print such a much bigger image than before, but where ON1’s NoNoise AI really shines is in high ISO wildlife photography . I’ve also had varying success depending on the animal in the photo and it really depends on the clarity of the original image.

I’d love to hear about your experience with AI-based noise reduction software. Share some of your before and afters in the comments below, because I’d love to see how far you can take this technology. I’ll have a future article coming out that will look at AI sharpening and its importance for landscapes, so be on the lookout for that.

Leave a Comment