The A.I. Evolution behind Topaz A.I. Clear

After a lot of effort from our team,  I am excited to share the latest version of A.I. Clear with you.  Topaz A.I. Clear is a software to remove photo noise and enhance sharpness. The update of A.I. Clear in Topaz Studio v1.12.5 is a completely new development. Not only does the new A.I. Clear do a better job of suppressing the noise, but further utilizes A.I. technology to transform noisy and blurry images into crisp and detailed images.

As a researcher in image processing for over 30 years, I cannot help but feel a little giddy about what our team has done.  Just take a look at the image above. Look at the clean removal of the noise. More importantly, look at the details in the output image!

It was a long journey to get here. Topaz Labs has always been at the forefront of image noise reduction. In 2010, Topaz Denoise had been already considered the best high-iso noise removal software in the market, a position it has maintained to this day.  The reason is that Topaz Denoise employed an algorithm that approached a theoretical upper-bound in terms of SNR (signal to noise ratio) increase. Therefore there were no much room for us, or anyone else for this matter, to improve it substantially. That is, until deep-learning in Artificial Intelligence (A.I.) emerged.

Hover over the blue plus signs to see more information.



Topaz Studio Ai Clear comes with three distinct neural networks, each trained specifically on a set of images with specific noise and detail requirements.


With one click, AI Clear automatically sets the noise reduction level using artificial intelligence to determine what setting is best for your image.


The Fastest of the three models, the Low setting is best for images with a range of subjects and a low to moderate amount of color noise. Cityscapes, landscapes, and architecture are great use cases for this model.


With Double the complexity of the Low model, the Medium setting is best for images with a defined subject and a moderate amount of noise and artifacts. This setting is particularly good on portraits and skin.


With double the complexity of the Low model, the High setting is best for images with a high amount of noise and artifacts. Evening shots, Long Exposures and Mid to High ISO images are cleaned and sharpened with this setting.


The new Enhance Sharpness feature allows you to manipulate the detail in your image to bring dull features back to life.


The Low setting is best for images with a smaller group of subjects. Works well on portraits, telephoto images, and astrophotography.


The High setting is best with a lot of small detail. This model works especially well with landscape photography.


If you find AI Clear to be removing a bit too much detail, increasing the value of this slider will bring back details that are removed by the adjustment.


Use this slider to increase or decrease the exposure of your result, higher values increase exposure, lower values decrease exposure.


Use this slider to increase or decrease the edge contrast of your image. Higher values increase edge visibility, lower values blend edges into surrounding detail .

A few years ago, the deep-learning based photo noise reduction in research started to produce a more promising result. A.I. Clear is the first commercial software that took advantage of this development.  It uses a “feedforward” neural network trained to suppress input image noise as much as possible. This type of method had proven itself to beat all known traditional methods in a research environment. Since Topaz Studio is an interactive app, the challenge was to discover a neural network architecture that could produce a good result at an interactive speed.  Through some pretty hardcore development work, we managed to deliver the first version of A.I. Clear, which produced better noise suppression than traditional methods without the need to manually fine tune every parameter. The reception from our customers was exceptional.

Then we began working on A.I. Gigapixel, the first deep learning desktop tool to enlarge photos. This long and detailed process vastly increased our understanding of A.I. based image enhancement. A.I. Gigapixel is based on a revolutionary concept in deep-learning called GAN (Generative Adversarial Network). It uses a “generative” neural network to synthesize plausible details that are non-existent in the input images. This process produces an unprecedented image enlargement result. The feedback for A.I. Gigapixel was so beyond our expectations and we knew we needed to use this technology for other purposes.

After the A.I. Gigapixel release, it was natural for us to try the same “generative” neural network idea on noise reduction and detail enhancement. So we did.  As expected, the “generative network” did not disappoint us.

But there was a catch. To produce the best result, this “generative” neural network needed a few orders of magnitude more “neurons and synapses” than the original one.  This much more complex network led to a very slow processing speed – an obvious no-go in an interactive app like A.I. Clear.  

Wanna Learn More?

Check out the AI Clear product page to learn more about AI Clear including pricing and to see more examples.

Eventually, our research scientist Dr. Acharjee found a pretty good compromise.  Through the work of our incredible development team, we managed to create a process that uses one-tenth the number of “neurons” than what we had started with. Not only did we match our previous speed – we exceeded it. Now, the speed is 2 to 3 times faster than the previous version of A.I. Clear, and we’ve improved image quality in most of our tests.  Still, for high noisy or blurry images it tends to synthesize unnatural-looking patterns (see image below) due to lack of enough “neurons” to remember the proper patterns.

While it was a pity that we could not put our best but admittedly slow neural network into A.I. Clear, we’re working on using this neural network in other ways. We’ve got a batch process image enhancer in the works that will use the no-compromise large neural network for those who want the very best possible result that A.I. technology can offer – regardless of how long it takes. A.I. Clear is impressive in what it can do, and even more capable technology is coming.

For now, I am excited to share the new A.I Clear with you. What do you think?

About the Author

About Albert Yang

Albert Yang founded Topaz Labs over 10 years ago, to form a company that adopts and implements the latest technology to introduce cutting-edge tools to the Photo market. With over 30 years of programming experience, he’s proud to offer his technical expertise to our users as the primary developer of our latest tools.

29 thoughts on “The A.I. Evolution behind Topaz A.I. Clear

  1. Hi,
    when I read about the neural network that is supposed to improve images without compromise, no matter how long it takes, I had to grin broadly.

    However, the quality, speed and selective improvement update was necessary to use the software in daily use.
    I am one of those annoying people on “Bird” who give you regular feedback, it is probably not the best place to do this.

    maybe we can use another way.

    By the way, A.I. Clear is the best software for pixelpeepers and people who take macro photos.

    1. Thomas,
      Thanks so much for the feedback. You can always submit feedback to our support team as well. Twitter isn’t really the best place because it tends to get noisy, however feedback here also works. Thanks for being a loyal Topaz Customer.

  2. Hi Greg,
    This is Khoa Vu. I was the last guy who met you and purchased your product at the SEMINAR in Lovonia Michigan couple days ago. How could I download and use the A.I ? Yes help.
    Thank you very much !

    1. Khoa,
      If you’re wanting to use A.I> Clear you’ll need to download and install Topaz Studio. The card you have your registration key on should have the steps you need on it.

  3. hello,
    looks great and i am going to update.
    However with my d750 even at 3200iso i have very few noise.
    is it recommended to launch AI clear from lightroom, so on a tif file instead of raw file ?
    do we need to disable noise reduction in lightroom before ?

    i am especially waiting now for the AI substitute of ADJUST plugin!

    best regards

    1. Hey Marc,
      Thanks so much for the feedback. If you’re sending files from Lightroom to Studio for processing in A.I. Clear, you’ll want to remove the default sharpening and noise reduction that Lightroom applies by default. I always do the TIFF conversion as well, it doesn’t hurt and that way you still have both files in your library.

  4. I recently purchased A.I. Clear and have seen amazing results with just one push of the button! This is another incredible tool from Topaz that everyone should have in their creative arsenal!


    Rod Neil Thomas
    Still Life Artist And Photographer

    1. Rod,
      Thanks so much!

  5. This is amazing. It will dramatically reduce the cost of upgrading my camera to a pro-level, while getting the results close to what could have been. Thanks!

    1. Chong,
      Thanks so much for the feedback! It’s our pleasure!

  6. Great things to come. A good idea to have a “fast” and a “very best system” to choose from.

    1. Hugh,
      Thanks for the feedback!

  7. I appreciate the development history and details. As a former electronics engineer I am somewhat familiar at the effort it takes to make things work. I have been using AI Clear from its release and I think it has been substantially improved in this new version. I also use Gigapixel and it is now fast and works great for enlargement. I would like to be able to use my own suffix (_GP) in Gigapixel and have it remember it, in some update. Thanks Topaz for the hard work and great products.

  8. In general, I prefer to not have to jump out to plug ins while processing my images (and for awhile I stayed within the Lightroom/Photoshop universe exclusively) but between the advances in Topaz Studio and AI Clear you have made their use in my workflow a necessary, routine and convenient step. My only wish now is that Lightroom would accept the updated file back a little quicker. Keep up the great work. Your products have become an invaluable part of my workflow.

    1. John,
      Thanks so much for the feedback. We’re so happy you’re loving Studio! I’ve passed this on to the rest of the team.
      Thanks for being a Topaz Customer.

  9. Congratulations on both AI Gigapixe and AI Clear, I have to agree totally that as a photographer, computer consultant, and former research scientist, every claim you make about these improvements is absolutely true. Old, decrepit scanned images, are improved beyond belief. It’s almost like a miracle.
    Before all of this goes to your head too much, I agree with Ron Lashley, comment that, we would very much appreciate, some more attention to allowing the user to customize these great programs, one example of which is a setting, in Preferences, for using our own suffix (GP_), or prefix (GPix ) or whatever. For AI Gigapixel, for example, it would be wonderful to not have to specify the output as JPEG, or TIFF, or PNG, but have the program automatically use the very same format as the input file. Also how about, allowing entire set of folders to be loaded into AI Gigapixel, since it uses is a batch processing technique. Thus it could work overnight. Perhaps it could even, create a subfolder of the input folder into which all of the processed files would be put.
    Finally, I want to thank you for all of the superb plugins and graphic processing environments that Topaz has created, as well as the fair pricing, and extremely generous treatment of your customers. I have always recommened Topaz products to all of my customers and friends and they have never failed, after trying them, to thank me profusely.

    A huge thank you to the entire Topaz Team,
    Dan Tong

    1. Dan,
      Thanks so much for your feedback! We’re happy you like our software! We’ll definitely look into adding custom persisting suffixes or prefixes to replace the default “_output” suffix.

      I thought I’d mention that in Gigapixel there is already the ability to maintain file types except when you’re processing RAW images. All you need to do it make sure you check the “Convert Raw Files Only” radial option, all processed images will maintain their original file types.

      Again, Thanks so much for your feedback I’ll pass it on to the rest of the team.

      1. I also had some suggestion to improve AI Gigapixel’s usefulness for heavy duty batch processing.
        It would be extremely useful to be able to load entire folders into the program and specify, the type of processing (upscale size, amount of noise reduction) , as well as the output folder location.
        Great work !

  10. Being able to add a suffix after a process’s would be a brilliant idea,
    Sending images to various software to process is history hard to define when searching files, or is there a way I have overlooked without segregation to another file.
    The only other option I know, is to manually add your own code in ‘Save as’
    However, it would be nice to opt for auto adds,so all you do is move onto the next image
    Then in file menu.settings, option to include in listing channel would reveal.
    That way it would not alter the type of file necessary for all software to define if it has ability to open particular ile. I.e. Jpeg, or text?
    Maybe, it is Microsoft or yourselves could have an answer?

    1. Richard,
      Our other batching application standalone A.I. Gigapixel has this functionality, also if you batch process in Studio, you can add custom filenames to your processed images. Check out this post for more info.

  11. Very interesting post, thank you. I have been a Topaz DeNoise user for several years but for certain categories of work I have had to use another noise reduction program because of its batch mode handling.

    I would be very interested to learn more about the batch mode processing you are hoping to introduce. While I realise that this is work that is under development, I have unexpectedly found myself to be in the market for a new graphics card. Would a batch mode processor be likely to use a graphics card to process the images? I have no real need for a high-end card just now but my buying decision may change if a future AI Clear would make use of the extra processing power.

    1. Hello,
      All of our A.I. Products utilize GPU processing to enhance and process images. So if you bought a more powerful GPU you’d see increased performancve from any of the Topaz Studio products as well as A.I. Gigapixel.

      1. Much appreciated, thank you

    2. Hello,
      All of our A.I. Products utilize GPU processing to enhance and process images. So if you bought a more powerful GPU you’d see increased performance from any of the Topaz Studio products as well as A.I. Gigapixel.

  12. I already have AI Gigapixel and it is brilliant – and I also prefer standalone products rather than completely integrated ones.
    Is there any likelihood that AI Clear wil also be produced as a standalone program?

  13. So I buy AI Clear and can’t find access to it anywhere. I was told to go to help and sync the plugin…did that and nothing, Nothing in LR, nothing in PS. then I bought Ai Gigapixel as a stand alone and that works fine. Am I missing something here????

    1. Douglas,
      AI Clear is a Pro Adjustment for Topaz Studio, not a standalone product. If you install studio from the downloads page, you’ll see it in the Adjustment Menu, as it shows on the interface screenshot on the product page here:

  14. Re: AI Gigapixel
    There is a very serious problem with processing PNG files with transparency. Many of these files crash the program at the very end of processing, suggesting that the problem lies with writing the file, this has been a problem since version 2.00, and persists with the latest update 2.1.1, whereas prior versions, other than the latest one in the versions worked fine with these PNG files. I’ve brought this up in the Topaz Forums and I’m disappointed that it still has not been fixed.

  15. AI Clear is the best noise reduction program that improves the sharpness at the same time.
    I’m excited. Although I am not good at English, I can handle topaz studio very well.
    topaz at some point in German language.

Leave a Reply

Your email address will not be published. Required fields are marked *

You'll receive your trial download and account through email.