topic Re: How to make the Neural Network Image Processing tool actually work. in Camera Software

How to make the Neural Network Image Processing tool actually work.

STS21 — Wed, 20 Aug 2025 16:39:53 GMT

In a Canon USA thread (https://community.usa.canon.com/.../Canon.../m-p/395278...) I found this: 'It needs a keyboard shortcut to invoke the process'.

I've tried using the tool but it makes absolutely no difference to the images, no matter where I put the two sliders. The manual is brief to the point of being almost useless so I'm wondering if this 'keyboard shortcut' is the missing piece in the puzzle.

Any help gratefully received,

STS21

Re: How to make the Neural Network Image Processing tool actually work.

John_Q — Fri, 22 Aug 2025 22:10:05 GMT

Hello STS21,

I was unable to access the page on the link that you provided unfortunately. Something like this, you may want contact a phone representative for assistance in real-time. If you would like to speak with a Canon representative, please contact our Technical Support Team at 1-800-652-2666, Monday through Friday between 9:00 am to 6:00 pm ET.

Re: How to make the Neural Network Image Processing tool actually work.

STS21 — Sat, 23 Aug 2025 15:02:46 GMT

Hi John,

The comment was on this thread by wq9nsc, posted on 12-08-2022:

Canon Community

Discussions & Help

Camera

Camera Software

Canon Neural Network Image Processing Tool - Softw...

Canon Neural Network Image Processing Tool - Software New Technology Release

Here's the relevant part of his post:

I purposefully shot some high ISO files last night at a girls' basketball game to give the neural networking tool a little test and I am fairly impressed with the results. And I like that it makes good use of the Nvidia GPU "Cuda cores" unlike DPP basic which has gotten better, the software is pretty fast on my dual CPU/dual Nvidia workstation graphics card system.

What I don't like:

1. It needs a keyboard shortcut to invoke the process, Canon does an excellent job of human factors interface with their 1 series bodies but their software frankly sucks in this important area. And don't prevent it from being invoked when in the crop window, just another useless slowdown that shows very poor attention to human factors. I am glad that the Canon software team doesn't design cars or aircraft.

2. Give us an option to auto close the stupid nag box once processing is completed. DPP updates always default to having to check the option box to close the image processed nag box but I don't even see the option box with the neural network tool.

Thanks for your reply,

Thomas

PS This came up when I tried to post my message today, though I don't understand what it means:

Your post has been changed because invalid HTML was found in the message body. The invalid HTML has been removed. Please review the message and submit the message when you are satisfied.

Re: How to make the Neural Network Image Processing tool actually work.

shadowsports — Sat, 23 Aug 2025 15:23:47 GMT

Greetings,

That message is in relation to the URL (link) you posted. I'm actually the author of thread you are referencing. It's here if you want to visit.

https://community.usa.canon.com/t5/Camera-Software/Canon-Neural-Network-Image-Processing-Tool-Software-New/td-p/395278#M13944

Re: How to make the Neural Network Image Processing tool actually work.

jrhoffman75 — Sat, 23 Aug 2025 15:41:18 GMT

@STS21 wrote:

Hi John,

The comment was on this thread by wq9nsc, posted on 12-08-2022:

Canon Community

Discussions & Help

Camera

Camera Software

Canon Neural Network Image Processing Tool - Softw...

Canon Neural Network Image Processing Tool - Software New Technology Release

Here's the relevant part of his post:

I purposefully shot some high ISO files last night at a girls' basketball game to give the neural networking tool a little test and I am fairly impressed with the results. And I like that it makes good use of the Nvidia GPU "Cuda cores" unlike DPP basic which has gotten better, the software is pretty fast on my dual CPU/dual Nvidia workstation graphics card system.

What I don't like:

1. It needs a keyboard shortcut to invoke the process, Canon does an excellent job of human factors interface with their 1 series bodies but their software frankly sucks in this important area. And don't prevent it from being invoked when in the crop window, just another useless slowdown that shows very poor attention to human factors. I am glad that the Canon software team doesn't design cars or aircraft.

2. Give us an option to auto close the stupid nag box once processing is completed. DPP updates always default to having to check the option box to close the image processed nag box but I don't even see the option box with the neural network tool.

Thanks for your reply,

Thomas

PS This came up when I tried to post my message today, though I don't understand what it means:

Your post has been changed because invalid HTML was found in the message body. The invalid HTML has been removed. Please review the message and submit the message when you are satisfied.

Hi Perhaps what Rodger meant is "It should have/allow a keyboard shortcut" DPP4 updates have occurred since his post.

DPP4 has a button to invoke the process in Extended functions.

Re: How to make the Neural Network Image Processing tool actually work.

jrhoffman75 — Sat, 23 Aug 2025 15:43:43 GMT

Re: How to make the Neural Network Image Processing tool actually work.

STS21 — Sat, 23 Aug 2025 16:33:46 GMT

Thanks John.

On my PC that option is greyed out, even with NNIPT open on a window 'behind' the DPP4 window as well as when I haven't opened NNIPT.

I can get files into the NNIPT window by clicking on 'Add' but nothing seems to have happened by the end of the process (a couple of minutes or so), when I compare the original CR3 files with the Nn.CR3 ones that had been generated.

I've just noticed that the 'Output file format' drop-down offers two options: .CR3 or .CRN Do I need to select .CRN or does that happen automatically? When I tried using NNIPT recently, files were created in DPP4 beside the original RAW files, with the suffix Nn.CR3. I assumed that was as it ought to be but maybe not?

Yours gratefully,

Thomas

Re: How to make the Neural Network Image Processing tool actually work.

STS21 — Sat, 23 Aug 2025 18:58:15 GMT

Hi shadowsports,

Apologies for posting the link without checking with you first that it was OK to do so.

Thank you for posting the whole link here.

Best wishes,

Thomas

Re: How to make the Neural Network Image Processing tool actually work.

Sports_N_stuff — Thu, 04 Sep 2025 20:14:07 GMT

Just started playing with it today. These are my early observations

It is a little klunky to get started. You're basically trying to surface a dialog box, which will show the file name of what ever file you've got highlighted and you can add more. You surface the box by going to "extended functions" and then "Start neural network image processing tool." It will open up a second DDP box on your task bar which you may have to click on it show on top of DPP.

Re. Your earlier questions

You can save in either format and see an improvement in the JPEG it will produce not sure if the CRN is the better of the two. Have been using the CRN so far. As the software notes, the "demosiacing" process is not included if you output to CR3, which has something to do with converting from RAW to image in your software. Not sure I'm doing it right, but my install seems to write over the original CR3. You'll note that the CRN is a gigantic file whereas the CR3 stays small and makes JPEGs that are even smaller than the original form of the CR3.

Does it do anything? I think so. Quite a bit actually. Depends on the shot though. When I'm pulling more detail into faces that I'm cropping out of a tiny area the effect is modest. At least it is for an R5ii image on a 70-200 2.8. E.G. if I've got a human head that is 8% of the image area width and 5% of the height, it will definitely smooth out the noise from that camera, and give a somewhat better definition to the eye bulges and the seam under the lower lid. It's not going to surface eyelash streaks out of that dark patch. Is it enough to turn a discard into a keeper? Maybe, if I'm willing to drop my standards a bit for clarity. I'm considering it. On a subject with firmer edges it seems to make a noticeable difference. 2nd E.G. a close-up on the coach's face. Dark lighting & noisy as usual on the bottom of the face. head width is about 16% of narrow image dimension - this time shot with an R1. Big difference decisively moves something out of the "if I have to" or "junk" folder into the keeper folder. chin wisker clouds surface about half the individual whiskers. Even more so with fuzz area that was on top of bald area. The arc, shape and expression of the ridge in his nose takes on dimension. The story is now the intensity with which he is addressing his team. A line on the shoulder becomes individual stitching. Dark fabric aqquires a texture. Brighten in DPP, lift the darks and it's a keeper. 3rd EG R5ii again. Head is about 8% of width. Definitely improves the scattered noise an R5ii will impart in these situations. Some additional detail? Yeah. maybe. Some. I don't use the R5ii as much so that may be part of it. Lack of experience. And it's not going to focus in at the speed you need it like an R1. And I think there may just be more residual background data lurking somewhere in an R1 image file.

As you might expect from a Canon product, I'm not seeing any full "pedal-to-the-metal" settings or output. they try to keep you from hurting yourselve. I've not yet been able to produce images that look like bent plastic as I might wander into trying to rescue something in Topaz. Neural network models tend to jump to conclusions and can insert things that aren't there if you don't know what you're doing but when this tool isn't having much effect, it also doesn't seem to break things. Have not been able to make it put a Topaz type distortion on letters but haven't really tried yet. Have seen it pull embroidery stitching lines out of a letter where you could barely tell they might be there before. Again depends on the picture and how much it can latch on. Haven't yet compared Topaz with Canon's NNIP on an image. In the cases where it can latch on, I'm thinking it might be better.

As best I can tell you're trying to surface a dialog box which will show the name of whatever file you're touching and you can add more. Neural networks are not tiny technology and they take a while to generate the "CRN" file. Similar to the time it takes to compute, smooth and draw a JPEG from a raw file. Don't know much about cuda cores, but it does stack up a few cores with minor loads on my AMD chip. I'm guessing that applying a NN to an image file doesn't distribute as well as basic image processing.

Overall, the didn't invest much in the interface, and the way it behaves with multiple windows enlarged is annoying but overall it seems like it might have soldi fundamentals at a good price.

Re: How to make the Neural Network Image Processing tool actually work.

Sports_N_stuff — Thu, 04 Sep 2025 20:16:52 GMT

... love the idea that I can access and launch this on files directly in DPP

Re: How to make the Neural Network Image Processing tool actually work.

jrhoffman75 — Thu, 04 Sep 2025 23:55:11 GMT

Good info. I think you forgot to post the images you are describing.

Re: How to make the Neural Network Image Processing tool actually work.

jrhoffman75 — Fri, 05 Sep 2025 12:43:50 GMT

I did a quick test with NNI tool.

The image was late dusk. It is underexposed - I limited the ISO to 25600 and shutter speed to 1/60.

Screenshot of original image.

100% crop of original image.

100% crop of NNI tool output. Increased Sharpness to 4 in DPP4.

Next test will be to output just a .CR3 file and then process to see what the difference is.

Re: How to make the Neural Network Image Processing tool actually work.

jrhoffman75 — Fri, 05 Sep 2025 19:08:30 GMT

The NN suffix file can be opened in DPP4 but isn't recognized by Lightroom.

The .CR3 file generated by NNI starts out looking "better" (less noise) than the original .CR3 but processing in LrC produces pretty close results for both. Slightly more noise for the non-NN version. (Adobe Adaptive Color profile and AI Denoise were used on both images.)

Re: How to make the Neural Network Image Processing tool actually work.

Sports_N_stuff — Sat, 06 Sep 2025 16:07:44 GMT

So, when you are asking the NNiP to generate a CR3 file you'll notice that it alerts you to say it won't be applying the neural network algorithm to "demosaicing." And you'll notice you get a smaller file than you would with a .CRN file.

What it's trying to tell you is this: There are two advantages you can gain from this additional out-of-camera processing with Canon's advanced statistical image models: 1) additional elimination of noise, and 2) Deeper processing of the RAW file to find additional fine detail within the image. To distinguish the level of processing a given file has endured, they will only eliminate noise when you save it as a CR3 file. If you want to benefit from additional interpretation of the original pixels in RAW you indicate that by saving as a CRN. When you have an image that benefits from this treatment, you'll notice that the additional detail can create a substantially larger file. When you have an image that benefits from additional processing you will see the most benefit when you let it save to a CRN file.

If you're most comfortable using external products like LRc, Topaz, etc. You can open the CRN file and save it as a TIFF file. Saving to this universal format will allow you to save most of the benefits of Canon processing while using other tools.

Re: How to make the Neural Network Image Processing tool actually work.

Sports_N_stuff — Sat, 06 Sep 2025 22:08:02 GMT

.. so doing some follow-up testing in Lightroom, with an actual photo I had been upgrading for submission in DPP4, I do find that a CRN file saved as a TIFF does save virtually all of the Canon enhancements when imported into LRc. To my eye, the coloration and dynamic range in the DPP4 - generated image is ever so slightly better, so that the rounding of the facial features might be a little more realistic, but that's just a bias of mine and they are essentially the same. I tried both a straight NN-based CRN, saved as a TIFF in DPP4 as well as a CRN saved as a TIFF, which underwent a shade of additional focus-polishing in Topaz saved as another TIFF and LRc was able to produce a JPEG image from both of these that was essentially comparable to DPP4. An additional advantage in this scenario is that DPP has already filtered out the noise. For me, if I'm trying to export a regular CR3 from LRc as a JPEG, I have to tune it a bit to get rid of the pixel grain in LRc: Turn the detail down to 0 and run denoise for about 30 seconds to match the image quality I get out of DPP4. The DPP4-generated TIFF already has that denoising/degraining baked into it even for the NN-based files.

Re: How to make the Neural Network Image Processing tool actually work.

Sports_N_stuff — Tue, 09 Sep 2025 19:52:49 GMT

Oh yeah! When you click on the image posted above, letting it go full screen, and cycle between the two you do see the difference in noise. Sweet.

Re: How to make the Neural Network Image Processing tool actually work.

JamesHarvey — Tue, 23 Sep 2025 22:31:22 GMT

From which camera body, with which FW release, did the images come from on which you noticed no change?

Thanks, I find the same, but only with one of my 3 (different model) bodies. With the other two the improvements from NN are outstanding. I'm going to start a thread on this issue that you may want to follow.

/JH