Three auto-colourising websites compared: bringing colour to monochrome images (part 1)

In this article, I will compare the automatic colourising services colorize-it.com, colourise.sg and auto-colorizer.com to hopefully offer you some perspective of how useful they are, individually and collectively.

I will always present the original colour image after the various auto-colourising outcomes, not necessarily in expectation of getting the exact same result back but at least to offer some perspective against which to compare the results.

NB auto-colorizer produces only a small “free” output image, which is used throughout.

Sample 1 (landscape, dawn/dusk)

Image taken from promotional material for the upcoming Joker movie. The intention was to use material that the algorithms would have been unlikely to be trained on.

joker_mono_sml
Black and white input
e3ed20ac802b42a0bd030b698f81d0b3_4b855216-642f-4ecc-9d82-5dd7c6692ff5
Result from colorize-it.com
colorized-image
Result from colourise.sg
tnc-1563284024-joker_monochrome
Result from auto-colorizer.com
joker_colour_sml
Colour original

My take: Auto-colorizer seems to have an inkling that there’s a colour gradient. For colourise.sg, skies seem to be blue, no questions asked. To be fair, whether the colour gradiant is real of added in post-production could be up for debate. It’s a close call, but of the three colourisations, the colourise.sg image would probably most convince me that it’s real.

Sample 2 (night street scene with neon displays)

Same source.

streetMonoSml
Monochrome input
98d26663320f2adc968b61e0d44216ad_d4611965-eda2-4853-8ad8-9c784c7c48d0.png
Result from colorize-it.com
colorized-image(1).jpg
Result from colourise.sg
tnc-1563285088-streetMono
Result from auto-colorizer.com
streetColorSml
Colour original

My take: I found it interesting that none of the algorithms are sufficiently familiar with traffic lights to know that when there are three round things one above the other, the bottom one is green and so on. Also, none of them seem to put ANY hue differentiation into the output. You’re basically getting a monochrome image back – just with a colour cast and in one case, even that is faint.

Sample 3 (indoor portrait, Caucasian female)

The subject here is the artist Anne Maria Udsen via Wikimedia Commons.

Anne_Marie_UdsenMonoSml
Monochrome input
511db5a9269e8c80ccb917b67a279058_9aab6d5e-5b59-4969-8f29-6160536f2f58
Result from colorize-it.com
colorized-image(2)
Result from colourise.sg
tnc-1563285678-Anne_Marie_UdsenMono
Result from auto-colorizer.com
Anne_Marie_UdsenSml
Colour original

It’s very clear that the Singaporean effort was more carefully trained on images of people.

My take: At this point, it seems that colorize-it hardly works at all. It just makes everything red to varying degrees. Colourise.sg produced a startlingly good image for once.

Sample 4 (clown stage portrait)

This is a portrait of Lasse Beischer as a clown. Source.

Lasse_Beischer_(2686825990)monoSml
Monochrome input
699c20d456f399a6a00624cf7b94b012_518c7566-40cd-4e8f-94a0-6050b7a9abcf
Result from colorize-it.com
colorized-image(3)
Result from colourise.sg
Lasse_Beischer_(2686825990)sml.jpg
Colour original

My take: Colorize-it seems to have landed a lucky punch for once, almost as though this or a similar image was in the training set. auto-colorizer did not produce output – it seems the clown broke the machine. I tried several times, but no luck with this image.

Sample 5 (daytime landscape with rainbow)

Double-alaskan-rainbowMonoSml.jpg
Monochrome input
00c7b3ef2156e6d520d0fdb8f1603b3e_b0954e6b-c0db-4a25-a2f5-e0ae458f7fed.png
Result from colorize-it.com
colorized-image(4)
Result from colourise.sg
tnc-1563308003-Double-alaskan-rainbowMono
Result from auto-colorizer.com
Double-alaskan-rainbowSml.jpg
Colour original

My take: Quite a mixed bag. Auto-colorizer produced the most unappetising vegetation of the three. None of them correctly recover the rainbow.

Sample 6 (outdoor movie scene, colourful clothing)

Screen Shot 2019-07-19 at 21.54.38monosml
Monochrome input
11fff1882134b2f9616a3a5f91551d4e_c18fe5c7-0a70-49da-af05-c00d6c918833.png
Result from colorize-it.com
colorized-imageSml
Result from colourise.sg
tnc-1563566543-Screen-Shot-2019-07-19-at-21.54.38mono
Result from auto-colorizer.com
Screen Shot 2019-07-19 at 21.54.38sml
Colour original

My take: It looks like colourise.sg takes the approach of not colouring areas at all if it’s not sure about them, and auto-colorizer may be doing something similar. Even colorize-it left an uncoloured patch. As for good news, all recovered the dark skin tone at least somewhat correctly, to varying degrees of interpretation.

Sample 7 (iconic movie shot, strong colour)

greenbookmonosml
Monochrome input
e3c4577fc4fae85554f9de603b288e20_e235d96f-9430-4708-96b5-1b2ee3bb6496.png
Result from colorize-it.com
colorized-image(1)sml
Result from colourise.sg
tnc-1563633051-greenbookmono
Result from auto-colorizer.com
GreenbookcolourSmall
Colour original

My take: In a nutshell, sky and skintones are reliable, but nothing else is. auto-colorizer seems to be the only one to correctly identify the blurred vegetation. On the other hand, colorize-it produced some more interesting colour, which I found engaging in spite of occasional imperfections, especially to do with edge recognition. Still, in this task, it’s my personal favourite out of the three.

And on to part 2…

Sorry for making this a cliffhanger, but since this is quite a long read already, I’ll give you my conclusions in part 2.

Advertisements

One comment

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.