Three auto-colourising websites compared: bringing colour to monochrome images (part 2)

As a final test after part 1, I was curious if I could push any of the algorithms into giving me some real initiative on colour by placing them in a situation where the subject was recognisable as an object that typically has saturated colours in it. I was also curious whether the filename and metadata would be used as cues (spoiler: seems not).

Sample 8 (colourful balloons, minimalist)

balloons-1869790_smlmono
Monochrome input
d8c787a8dc9516d0e952aa0caf3ed4b7_d87fe8f4-d32f-4a09-84be-1e0eeb05c2d9.png
Result from colorize-it.com
colorized-image(5)sml
Result from colourise.sg
tnc-1563309143-balloons-1869790_1920mono
Result from auto-colorizer.com
balloons-1869790_sml
Colour original

My take: colorize-it balloons look like oranges and colourise.sg ones like eggs. At this point, I’m not sure these programs know what balloons are.

Sample 9 (hot air balloon)

abstract-1867656_smlmono
Monochrome input
b0d904e1b87adce2b30a3ccaed593479_a111b946-bb43-4ee8-a34f-e784f3d3be46.png
Result from colorize-it.com
colorized-image(6)sml
Result from colourise.sg
tnc-1563309344-abstract-1867656_1920mono
Result from auto-colorizer.com
abstract-1867656_sml
Colour original

My take: colorize-it’s ability to sometimes generate engaging colour where the others cannot, is what you’ll want to keep it around for.

Sample 10 (colourful balloons, abstract)

balloons-1761634_smlmono
Monochrome input
1406ed641fe412a5b74863ff1bbfa0ef_a6ba60a7-d326-4a28-9b93-3df746313c67
Result from colorize-it.com
colorized-image(7)sml
Result from colourise.sg
tnc-1563309669-balloons-1761634_1920mono
Result from auto-colorizer.com
balloons-1761634_sml
Colour original

My take: By this point, it’s clear that colourise.sg thinks balloon-shaped objects are eggs. It may have never actually seen balloons.

Sample 11 (woman with balloons)

pic1920monosml
Monochrome input
d160c1deebb4fcd4a880d738728eacaa_06f99b59-b438-4e56-b3a6-0f51aecd2a23
Result from colorize-it.com
colorized-image(3)sml
Result from colourise.sg
tnc-1563664247-pic1920mono
Result from auto-colorizer.com
balloons-388973_1920sml
Colour original

My take: The human element helps the AI understand that it’s looking at coloured balloons. Even colourise.sg caught on to this now and surprisingly gave the most colourful rendition, although it looks like that was partly because it conflated the colours with the sky. Still, much better than before. colorize-it.com is adventurous as ever. None could figure out that the road should be grey.

Sample 12 (berry kiwi salad)

fruit-2305192_monosml
Monochrome input
47c62f51be664ffac073ec1d721ecd7b_259db405-b1be-47c7-836d-92d40f6bd598
Result from colorize-it.com
colorized-image(2)sml
Result from colourise.sg
tnc-1563663711-fruit-2305192_mono
Result from auto-colorizer.com

My take: auto-colorizer recognises the raspberries, but is reticent to make strong colour choices. colorize-it is all over the shop again, hedging its bets by making some of the berries red and others green. colourise.sg doesn’t seem to know European berries.

I was also surprised that a simple texture like wood was unclear to all but auto-colorizer.

Sample 13 (furniture)

furniture-1840463_1920monosml
Monochrome input
3d4a85bff7b28343d85a69539c15598d_39654647-80ca-4110-9a69-597ecad684ca
Result from colorize-it.com
colorized-image(10)sml
Result from colourise.sg
tnc-1563697065-furniture-1840463_1920mono
Result from auto-colorizer.com
furniture-1840463_1920sml
Colour original

My take: colourise.sg works out a nice contrast between a reddish brown seat and the green plants by the window, while colorize-it and auto-colorizer return essentially monochrome images.

Sample 14 (boy with cat)

4151879_1920monosml
Monochrome input
be542c6266291e31fb78ae318a934e5e_a2b77e9f-882d-447e-b372-abe5d97cdd85.png
Result from colorize-it.com
colorized-image(13)sml
Result from colourise.sg
tnc-1563699784-4151879_1920mono
Result from auto-colorizer.com
4151879_1920sml
Colour original

My take: Colorize-it wins this one, hands down. I tried another cat image, but cat faces are apparently unknown to these colourisers. The take-home message surely is that the algorithms we have available are fairly good, but the training sets are now the limiting factor. With good training come good results.

Conclusions

First, the good news. In part 1, we saw that these auto-colourisers can often be trusted to produce good skin tones, in the sense that if you use three of them, at least one will turn out good. This can be a real time-saver for doing colourisation work.

Beyond that, auto-colourisers are a bit hit and miss. In this testing, none stood out as being consistently good. In fact, the most noteworthy feature I found is how conservative they are. They mostly avoid bold colours, especially mixing them in the same image, and sometimes don’t colour things at all. I can only assume that this is because the learning process placed heavy penalties on getting bold colours wrong so that it was better for the algorithms to err on the side of caution. Perhaps the way that colour deviations are calculated needs to be reconsidered in light of this.

While careful hand-colourising can in many cases no doubt get much better results, depending on one’s level of skill, some of the above images – especially of vegetation outdoors – provide useful starting points. In the colourise.sg rainbow image, the only thing missing not passably colourised was the actual rainbow, so a fair amount of work could theoretically be saved using this auto-colouriser – so long as it actually gives a good result.

For an actual colourising task, it’s probably worth running an image through a few of these automatic programs just to see if any of them produce useful results.

If I had to pick only one of these three, I would choose colourise.sg – it processes the fastest, provides the highest resolution download image, and is generally a safe choice when you don’t require strong colour. However, it doesn’t know much other than vegetation, sky and people (but the latter quite well and reliably). In spite of this, the resulting image isn’t usually worse than what you started with. In that context, it should be noted that it states clearly that it is intended “specifically for old Singaporean photos”, so I was pushing it beyond the original intention of the creators, but I think it did okay, keeping in mind how the others performed.

The second best option in my opinion is colorize-it.com. I could see myself keeping it in my arsenal for situation where I want bolder colours. It does come with some colour bleeding, though, so will require manual repair where that happens.

auto-colorizer cannot be recommended as it failed twice, once when processing the clown and a second time when processing an image of a mango fruit (not shown in my final report). Also, the payment option is displayed whether or not a result was generated, which could lead some people to attempt to pay and then find out they get nothing for their money – and the “tiny PayPal donation” turns out to be $10. (And the download resolution offered after payment is smaller than the free one from colourise.sg.)

Other recent AI-themed content

Screen Shot 2019-06-23 at 08.49.29
Moving photos and 3D: latest AI (beyond FakeApp)
CREATOR: gd-jpeg v1.0 (using IJG JPEG v62), quality = 60
What are the implications of DeepFake for society?
58d7005687456f7f1d8b46b6_da39a3ee5e6b4b0d3255bfef95601890afd80709
AI may split the camera market

 

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.