Color matching and prediction: color correction tool v1.3 released! — Page 8

It's really interesting how the colors really affect the depth and feel of a scene. The last picture has less visible detail than the bluray and WOWOW in the background, but it really puts Indy and the idol center stage. Also the greater contrast adds mystery and depth that is really missing in both the bluray and the WOWOW. 

DrDre said:

Another nice property of the color matching algorithm, is that it does not require the reference to have the same quality as the source. Although it's not Star Wars, I thought it was nice to share this comparison. There has been a lot of debate about the color timing of the Raiders of the Lost Ark bluray, and some prefer the HDTV broadcast known as the WOWOW. Here's an example of color correcting the bluray using a screenshot of a 16 mm print of Raiders of the Lost Ark, that has most of it's colors intact.

An interesting aspect of this color match, is that Indy has a more natural skin tone in the color corrected frame, than in either the bluray or the WOWOW. 

 That's really great looking, especially since I think that the Blu Ray looks better than WOWOW in that particular shot. That one just blows both of them out of the water.

nightstalkerpoet said:

I'd be far more interested in seeing Indy 4 color matched using the first 3 films.

 I'd be more interested in Indy 4 being more like the first 3.

Molly said:

WOWOW is a satellite TV network in Japan.

 Thanks, I was wondering where that weird name came from. :-)

Anyone interested in getting the color correction GUI can send me a PM. I will then send you a link to the necessary files.

When you've downloaded the file named ColorCorrect_pkg.exe, execute the file. You will be asked to install the MATLAB runtime environment. After you have finished installing, a new executable named ColorCorrect.exe will be available. Open this file as administrator, else it will not work. 

A few words of advice on using the GUI. The GUI itself is pretty self explanatory.

The process is as follows:

1) Select a test image. A figure will open, showing the image. You will be able to crop the frame, with your cursor.

2) Select a reference image. A figure will open, showing the image. You will be able to crop the frame, with your cursor.

3) Build a color correction model. Depending on the resolution/size of the images after cropping and your hardware, this may take 0-15 minutes (15 min for a 4K image) on an Intel Core i5. A figure will open showing you the test frame as it is being matched. With each iteration it should be closer to the reference.

4) Save the color correction model for later (optional).

5) Import a color correction model (optional).

6) Import any number of images, and color correct them with a color correction model you just built or imported. The images will be saved in a newly created directory named "Corrected" with the same name as the original images. Color correcting a frame may take anywhere between 5 and 20 seconds, depending on the resolution/size of the frame, and of course your hardware.

When building a color correction model you should consider the following:

1) The model assumes the test and reference images (frames) are identical, aside from the color. In other words it's important the images are cropped in the same way (to a reasonable degree). Incorrect cropping may lead to artifacts.

2) When using a print or a low quality source as a reference, there may be color variations within the frame. For example some parts may be darker or brighter than others. If you use the full frame for building a color correction model, it will try and fail to reconcile these differences, resulting in artifacts. The best way to go, is to select a consistent part of the frame, select the same part for the reference, and then build the color correction model. 

3) Although it is in theory you could regrade an entire film, based on a single reference frame, this will probably not work in practice, because one reel may have degraded in a different way than another or one scene may have been color graded differently from another. In principle it is possible that each frame will have to be matched individually, but usually a film is graded on a scene by scene basis, so a single reference will suffice for a particular scene. 

Hope you enjoy the tool. Of course if you use the tool for your projects, any acknowledgements will be appreciated. The same is true for any comments, critisism or suggestions you may have. In that case write a post in this thread or send me a PM. 

As I've shown before, the real power of this color correction method is the color prediction of other frames. Using the previous frame from Raiders of the Lost Ark as a reference (slightly adjusted), I predicted the colors for five frames from the beginning of the film:

This is the result. Who says you can't make the bluray look like film? ;-):

I actually did slightly correct the reference, before building a color correction model. It is very contrasty, but I think that's part of why it has that film like look. It would never look like this on a home video, but it does recreate the atmosphere of being in a theatre. Here are a few more iconic frames from the film adjusted by the model to match 16 mm colors:

After watching your colour matchings of I can say one problem with the special editions is that they altered the look of the OT to make them look like mid-90s movies to appear more "contemporary" instead of preserving the look of the late 70s-early 80s films they actually are.

Interestingly enough, the 35 mm scans provided by Harmy seem to suggest the film indeed was more contrasty than either the bluray or the WOWOW:

35 mm:

bluray corrected: 

Theatrical prints have always been more contrasty than video transfers. Theatrical-print contrast has never read well on TVs, which is why most transfers have come from low-contrast interpositives (except for more recent restorations scanned from original negatives and such). Even when they do boost the contrast, clip the whites and crush the blacks, it looks nothing like a theatrical print. We always see too much mid-range fill light. That shot of Alfred Molina looks so much better in your prediction than in the "before" image.

Amazing!

Interesting!  I wonder if someone can figure out how to turn the grade into a Truelight LUT!

Most impressive!

NeverarGreat said:

Quick comparison:

1: Blu-ray

2: Blu-ray with predictive colormatching from 16mm source

3: 35mm frame with slight color correction to remove red fading

4: Blu-ray with curves adjustment

While the colormatching algorithm works amazingly well when using identical shots, I'm not sold on its predictive power. In the above example, the predictive shot has crushed and dull highlights, and the blue in the background inexplicably turns to purple.

The model was not calibrated on a representative 35 mm frame, but on a 16 mm frame, so naturally it's not going to be able to predict the colors of a different print, and certainly not one in poor condition. However, if the source and reference quality is good, the predictions are usually very accurate in the same scene, and sometimes across scenes, as was evident from the Star Wars example:

Bluray:

Bluray matched to reference frame:

Bluray:

Bluray matched directly to Tech IB:

Predicted correction using color correction model from the above R2D2 reference frame:

Here's another example of prediction for the Raiders of the Lost Ark bluray, and WOWOW. First a color correction model was calibrated on this frame:

Bluray:

WOWOW:

Bluray matched to WOWOW:

Then I predicted the corrections for the following frames:

Bluray:

WOWOW:

Predicted correction with color correction model from the above reference frame:

Bluray:

WOWOW:

Predicted correction with color correction model from the above reference frame:

I decided to test it out last night on the Criterion & Arrow versions of Dress To Kill. Caps were grabbed from DVDBeaver.

Here's the Criterion Blu-Ray.

Here's the Arrow Blu-Ray.

Here's the Criterion Blu-Ray Color Matched to the Arrow Blu-Ray.

Other than a slightly pinker shade to Michael Caine's skin tone, the corrected image looks very accurate to the Arrow Blu-Ray.

I agree with Neverar. Dre, I'm certain that it was unintentional, but your Star Wars images there are literally the exact same url. Here's the comparison, at least using the images you had a couple days ago:

http://screenshotcomparison.com/comparison/142387/picture:2

You can see that it gives the same general impression and tones. But it's lacking the specifics and looks more homogeneous overall. The shadows look a bit funky, too. If you look at shots 1 and 4, I think there's really no competition. The specific match looks like a technicolor print. The non-specific looks like it's in the ballpark, but not right. 

The predictive ability is really neat that it even works as well as it does. A great proof of concept and I'm sure there will be cases where it's useful because of limited resources being available. Now, I'm not suggesting it needs to be frame by frame, but probably shot by shot or as new elements enter a shot. Applying one ref over a wide range of frames seems like it would be risky for introducing artifacts and incorrect color.

edit: I am curious if your second Indiana example WOWOW and Match might be identical images. It seems the actual WOWOW might be missing.

towne32 said:

I agree with Neverar. Dre, I'm certain that it was unintentional, but your Star Wars images there are literally the exact same url. Here's the comparison, at least using the images you had a couple days ago:

http://screenshotcomparison.com/comparison/142387/picture:2

You can see that it gives the same general impression and tones. But it's lacking the specifics and looks more homogeneous overall. The shadows look a bit funky, too. If you look at shots 1 and 4, I think there's really no competition. The specific match looks like a technicolor print. The non-specific looks like it's in the ballpark, but not right. 

The predictive ability is really neat that it even works as well as it does. A great proof of concept and I'm sure there will be cases where it's useful because of limited resources being available. Now, I'm not suggesting it needs to be frame by frame, but probably shot by shot or as new elements enter a shot. Applying one ref over a wide range of frames seems like it would be risky for introducing artifacts and incorrect color.

edit: I am curious if your second Indiana example WOWOW and Match might be identical images. It seems the actual WOWOW might be missing.

I replaced the duplicate images for both the Star Wars and Indy examples. I also switched to another image hosting site, because screenshotcomparison can be frustratingly unstable at times.

You actually used the C3PO/Owen image that did not have the correct cropping, so the colors came out wrong. The one that's in the example was the correct one, posted after neverar great noticed some problems. The correct prediction is very close.

Let me eleborate a bit in the next posts...

Generally, the further you go away from a reference frame, the worse the prediction. However, there are a couple of situations we can consider.

Let's consider the case that you want to match two good quality sources that have been color timed in a different way. It is possible that each frame was color timed differently, however usually the color timing within a shot or even in a whole scene are very similar. 

Here's an example for the Raiders bluray and the WOWOW. First the model is calibrated on this frame:

Bluray:

WOWOW:

Bluray matched to WOWOW:

First, I predicted the corrections for in the same scene, within the same shot:

Bluray:

WOWOW:

Predicted correction with color correction model from the above reference frame:

Then I predicted the corrections for in the same scene, but not within the same shot, where the color timing differences are expected to be larger:

Bluray:

WOWOW:

Predicted correction with color correction model from the above reference frame:

The prediction is still very close. The color of the whiskey is actually more consistent with the reference in the prediction, than in the actual WOWOW frame. Certainly far better than could have been done manually without a good reference, but we should be careful using frames from a different shot.