Comparison Testing AI Noise Reduction Programs for Astrophotography


The test compares six new AI-based noise reduction programs against the non-AI noise reduction offered by Adobe Camera Raw and Adobe Lightroom.



How well do new AI noise reduction programs work for astrophotography? I tested six to find out.


In the last two years we have seen a spate of specialized programs introduced for removing digital noise from photos. The new generation of software uses artificial intelligence (AI), aka machine learning, trained on thousands of images to better distinguish unwanted noise from desirable image content.

However, in astrophotography our main subjects – stars – can look a lot like specks of pixel-level noise. How well can each program reduce noise without eliminating stars or wanted details, or introducing odd artifacts, making images worse?

To find out, I tested six of the new AI-based programs on three sample astrophotos.


The benefit of AI-based noise reduction (at right) is that it can, in theory, remove noise more effectively than non-AI programs (at center) without harming details or sharpness.



In the test results for the three images below I show the original raw image plus a version with noise reduction and sharpening applied using Adobe Camera Raw’s (ACR) own sliders with luminance noise at 40, color noise at 25, and sharpening at 25.

I use this as a base comparison, as it has been the noise reduction software I have long applied to images. However, ACR’s routine (also found in Adobe Lightroom) has not changed in years. It is good, but it is not AI. 

I compare it to:


ON1 NoNoise AI 2023  Version tested: 17.0.1

Topaz DeNoise AI  Version tested: 3.7.0

Topaz Photo AI  Version tested: 1.0.9

Luminar Neo Noiseless AI  Version tested: 1.5.0

DxO PureRAW2  Version tested: 2.2

RC-Astro NoiseXTerminator  Version tested: 1.1.2, AI model 2 


Noise XTerminator is made specifically for astrophotos. The others are general purpose noise reduction programs. Click on the product names to go to their websites for more information and pricing.

While some of the programs can be used as stand-alone applications, I tested them all as plug-ins for Photoshop, applying each as a smart filter applied to a developed raw file brought into Photoshop as a Camera Raw smart object.

The exception is DxO’s PureRAW2. It can work only on raw files as a stand-alone app, or via an Adobe Lightroom plug-in that exports files to it. It does not work as a Photoshop plug-in. I tested PureRAW2 by dropping raw Canon CR3 files into the app and then exporting the results as raw DNG files. 


This shows the three test images, lightly processed in Adobe Camera Raw for color correction and contrast, before applying noise reduction with the various programs.


As shown above, I chose three representative images: 

  • A nightscape with star trails and a detailed foreground, taken at ISO 1600.
  • A wide-field deep-sky image at ISO 1600 with an 85mm lens, with very tiny stars.
  • A close-up deep-sky image taken with a telescope at a high ISO of 3200, showing thermal noise hot pixels. 

Each is a single image, not a stack of multiple images. 


This compares the programs on a typical nightscape image, with the inset showing the small area blown up in each panel. Of interest is how well each preserves ground detail.



As with all test images here, the panels show a highly magnified section of the image, indicated in the inset. I shot the image of Lake Louise in Banff, Alberta with a Canon RF15-35mm lens on a 45-megapixel Canon R5 camera at ISO 1600. 

  • Adobe Camera Raw’s basic noise reduction did a good job, but like all general routines it does soften the image as a by-product of smoothing out high-ISO noise.
  • ON1 NoNoise 2023 retained landscape detail better than ACR but softened the star trails, despite my adding sharpening. It also produced somewhat patchy noise smoothing in the sky. It left a uniform pixel-level mosaic effect in the shadow areas.
  • Topaz DeNoise AI did a better job than NoNoise AI, retaining the sharp ground detail while smoothing noise, always more obvious in the sky in such images. Even so, it also produced some patchiness, with some areas showing more noise than others.
  • Topaz Photo AI, despite being from the same company as DeNoise AI, did a poor job, producing lots of noisy artifacts in the sky and an over-sharpened foreground riddled with colorful speckling. 
  • Noiseless AI in Luminar Neo did a decent job smoothing noise while retaining – indeed sharpening – ground detail without introducing ringing or colorful edge artifacts. The sky was left with some patchiness and uneven noise smoothing.
  • DxO PureRAW2 smoothed noise very well while enhancing sharpness quite a lot, almost too much, though it did not introduce obvious edge artifacts. This was using its DeepPrime method. Its main drawback is that in making the conversion back to a raw DNG file it altered the appearance of the image, in this case darkening the image slightly.
  • Noise XTerminator really smoothed out the sky, and did so very uniformly without doing much harm to the star trails. However, it smoothed out ground detail unacceptably, which isn’t surprising given its specialized training on stars, not terrestrial content. 

Conclusion: For this image, I’d say Topaz DeNoise AI did the best, though not perfect, job. 

This was surprising, as tests I did with earlier versions of DeNoise AI for AstroGear Today showed it leaving many patchy artifacts and colored edges in places. Frankly, I was put off using it. However, Topaz has improved DeNoise AI a lot. 

NoiseXTerminator might be a good choice for reducing noise in just the sky of nightscape images. It is not suitable for foregrounds. This confirms earlier tests I did for AGT found here


This compares the programs on a tracked wide-field image to see how well each reduces noise without eliminating the tiny stars and deep-sky object details.



I shot this image of Andromeda and Triangulum with an 85mm Rokinon RF lens (tested here for AGT, though the lens is no longer available) on the 45-megapixel Canon R5 on a star tracker. Stars are points in these images, with small ones easily mistaken for noise. 

  • Adobe Camera Raw’s noise and sharpening routines do take care of the worst of the luminance and chrominance noise, but inevitably leave some graininess to the image. 
  • ON1 NoNoise 2023 did a better job than ACR, smoothing the worst of the noise, and doing so uniformly, without leaving uneven patchiness. However, it did soften star images, almost like it was applying a 1- or 2-pixel gaussian blur, adding a slight hazy look to the image. And yet the faintest stars were sharpened to one- or two-pixel points.
  • Topaz DeNoise AI did a better job than Camera Raw, though it wasn’t miles ahead. This was with its Standard setting. Standard didn’t erase stars; it actually sharpened the fainter ones, almost a little too much, making them look like specks of noise.
  • Topaz Photo AI again performed poorly. Its Normal mode left lots of noise and grainy artifacts. While its Strong mode shown here did smooth background noise better, it softened stars, wiping out the faint ones and leaving colored edges on the brighter ones. 
  • Noiseless AI in Luminar Neo did smooth fine noise somewhat, better than Camera Raw, but still left a grainy background, though with the stars mostly untouched in size and color. 
  • DxO PureRAW2 did eliminate noise quite well, while leaving even the faintest stars intact, unlike with the deep-sky image below, which is odd. However, it added some dark halos to bright stars from over-sharpening. And, as with the nightscape example, PureRAW’s output DNG was darker than the CR3 raw that went in.
  • Noise XTerminator performed superbly, as expected – after all, this is the subject matter it is trained to work on. It smoothed out random noise better than any of the other programs while leaving even the faintest stars untouched, in fact sharpening them slightly. Details in the little galaxy were also unharmed. 

Conclusion: The clear winner was NoiseXTerminator. 

Topaz DeNoise was a respectable second place, performing better than it had done on such images in earlier versions. Even so, it did alter the appearance of faint stars, which might not be desirable. 


This compares the programs on an image taken with a telescope to see how well each deals with thermal noise hot pixels and retains details in the nebulosity.



I shot this image of the NGC 7822 complex of nebulosity with a SharpStar 61mm refractor (reviewed here for AGT), using the red-sensitive 30-megapixel Canon Ra and a narrowband filter to isolate the red and green light of the nebulas.

No dark frames were applied, so the 8-minute exposure at ISO 3200 taken on a warm night shows thermal noise as “hot pixel” white specks.

  • Adobe Camera Raw did a good job smoothing the worst of the noise, suppressing the hot pixels but only by virtue of it softening all of the image slightly at the pixel level. However, it leaves most stars intact. 
  • ON1 NoNoise 2023 also did a good job smoothing noise while also seeming to boost contrast and structure slightly. But, as in the wide-field image, it did smooth out star images a little. This was with no sharpening applied and Luminosity at 60, down from the default 100 NoNoise applies without fail.
  • Topaz DeNoise AI did another good job smoothing noise, while leaving most stars unaffected. However, the faintest stars and hot pixels were sharpened to be more visible tiny specks, perhaps too much, even with Sharpening at its lowest level of 1 in Standard mode.
  • Topaz Photo AI again produced unusable results. Its Normal modes produced lots of mottled texture and haloed stars. Its Strong mode (shown here) did smooth noise better but still left lots of uneven artifacts, like DeNoise AI did in its early days.
  • Noiseless AI in Luminar Neo did smooth noise but unevenly, leaving lots of textured patches. Stars had grainy halos and the program increased contrast and saturation, adjustments usually best left for specific adjustment layers dedicated to the task. 
  • DxO PureRAW2 did smooth noise very well, including wiping out the faintest specks from hot pixels, but it also wiped out the faintest stars, I think unacceptably and more than other programs like DeNoise AI. For this image, it did leave basic brightness alone. However, it added an odd pixel-level mosaic-like effect on the sky background, again unacceptable.
  • Noise XTerminator did a great job smoothing random noise without affecting any stars or the nebulosity. The Detail level of 20 I used actually emphasized the faintest stars, but also the hot pixel specks. NoiseXTerminator can’t be counted on to eliminate thermal noise; that demands the application of dark frames and/or using dithering routines to shift each sub-frame image by a few pixels when autoguiding the telescope mount. Even so, Noise XTerminator is so good users might not need to shoot and stack as many images. 

Conclusion: Again, the winner was NoiseXTerminator. 

Deep-sky photographers have praised “NoiseX” for its effectiveness, either when applied early on in a PixInsight workflow or, as I do in Photoshop, as a smart filter to the base stacked image underlying other adjustment layers.

Topaz DeNoise AI is also a good choice as it can work well on many other types of images. But, again, play with its various models and settings. Pixel peep!

ON1 NoNoise AI 2023 did put in a respectable performance here, and it will no doubt improve; it had been out less than a month when I ran these tests. 

Based on its odd behavior and results in all three test images, I would not recommend DxO’s PureRAW2. Yes, it reduces noise but it can alter tone and color in the process. I consider that unacceptable.  


Most programs (Luminar Neo is an exception) are available as free trial copies to test out on your astro-images and in your preferred workflow.



The nature of AI means that the results will certainly vary from image to image. In addition, like all software, these AI programs are a moving target. All are being updated frequently with new AI models to improve noise reduction.

Even with the latest version installed, many of these programs offer multiple models and settings for strength and sharpening. Results from the same program can vary a lot. In this testing, I used either the program’s auto defaults or backed off those defaults where I thought the effect was too strong and detrimental to the image.

And do remember I’m testing on astrophotos, and pixel peeping to the extreme. Rave reviews claiming how well even the poor performers here work on “normal” images might well be valid. 

This is all by way of saying, your mileage may vary!

So don’t take my word for it. Download trial copies and test for yourself. But do pixel peep. That’s where you’ll see the flaws.



This review is an abridged version of one that appears in full at the author’s blog page here.

The full version of the review includes downloadable full-resolution images, a comparison of DeNoise AI’s various models, a comparison of DxO’s Prime vs DeepPrime, as well as comparisons of the best AI programs to the older non-AI programs, Nik Collection’s Dfine2 and Neat Image’s ReduceNoise9.



About Alan Dyer

Alan Dyer is an astrophotographer and astronomy author based in Alberta, Canada. His website at has galleries of his images, plus links to his product review blog posts, video tutorials, and ebooks on astrophotography.

Related posts