Hacker News new | past | comments | ask | show | jobs | submit login

I wrote a quick script the other day to colorize directories of family photos. I realized it would be cool to colorize these photos, too. Here's the album: https://imgur.com/a/aJbpMjf

The script uses the Image Colorization API from DeepAi.

Here's the repo for the colorizing model itself: https://github.com/jantic/DeOldify

I don't think the DeepAi API allows you to adjust the model parameters, but you definitely can if you run it yourself from the repo above or a colab instance (e.g. https://colab.research.google.com/github/jantic/DeOldify/blo...). MyHeritage also offers this API as a service with tunable parameters.

If you want some quick results on your own BW images, just set your own DeepAi API key as an env var and run this script: https://github.com/skzv/colorize-photos

This is fascinating, thank you. It’s hard to explain my color blindness to people and I’m inclined to begin with this HN thread in future.

I can differentiate color mostly fine and have never mis interpreted grass as green, but clothing and fabric always pose problems, just as with your AI.

I’ve learned to be ok with things not looking real. Black and white is just as unreal to me as false color toning, but feels more honest and deliberate. The luma of the Armalite wielding guerrilla is amazing — it’s hard to beat black and white as a descriptor format.

This is really great. Even if the colours might be off from actual reality, it brings it to life nonetheless.

You have successfully removed the visual excellence of those images.

This was really cool. Thank you for taking the time to put that together.


I can understand the concern. It can mislead people about what the past really looked like.

An example: this same model colorized the Golden Gate white: https://camo.githubusercontent.com/3487a03626fd86d4f8c814636...

In my case I wasn't too concerned, since I was sharing the photos with my family, who understood they were artificially colorized. My father even asked me if it was possible to choose specific colours in articles of clothing, since it got those wrong. Nonetheless, to me and my family, it made our old photographs seem so close and alive, which made it worth it.

A good compromise may be to mark these retouched photos with a small watermark indicating that they have been altered. By the way, I think the colab instances running this model have the option to add watermarks for this reason (https://colab.research.google.com/github/jantic/DeOldify/blo...).

> My father even asked me if it was possible to choose specific colours in articles of clothing, since it got those wrong.

Did you figure out a way to achieve this other than repeat attempts or recoloring in post?

Is there a setup that retrains with user input such as by inputting an image with an object manually colored the model will then recognize it in later input and color similarly?

It seems like this could also help with persistence of colors in videos, training with the previously completed frame step before producing the next.

Silly question, but was the bridge definitely painted red at that stage of its life?

Panchromatic vs orthochromatic was still a choice even in the 70s. Spotmatics shipped with an ISO marker dial that included color, ortho, and panchro, 30 years after the Golden Gate Bridge was built.

Ortho bw — cheap 1930s snapshot — would show a red bridge as white, but if it was fancy panchro then I’d be more inclined to agree with the AI, given the luminosity.

There was this incident from last month: https://www.aljazeera.com/news/2021/4/11/cambodia-condemns-v...

Cambodia has called on US media group Vice to withdraw an article that featured newly-colourised photographs of victims of the Khmer Rouge, saying the images are an insult to the dead because some had been altered to add smiles.

“We urge researchers, artists and the public not to manipulate any historical source to respect the victims,” [Cambodia’s Ministry of Culture] said.

I don't think it was just the colorizing that was the problem. He was changing their expressions into smiles!

I wonder at what point the photo would be colorized correctly. The golden gate bridge is almost certainly in the training data if it's random photos. Maybe it knows to color completed things?

what about photos that were taken in colors but then get edited to look a certain way (most of photos on the internet)?

and what about those space photos?

Even every photo you take with a smartphone these days is altered by a machine learned model, put through some filter, and tuned in some way, even if it's subtle.

I think that there’s a general understanding that cameras don’t match 100% what the eye sees. That’s different from a white golden gate.

people see a white golden gate and they immediately know that's not a realistic representation. They don't look at photos heavily touched or space photos with that expectation.

Was the Golden Gate bridge painted at that point? [1] says "some" of the steel came with red primer.


Why not? I've also colorized pictures and video frames using these same sorts of processes. It's reasonably quick and works pretty well

It’s fake, and pretty soon people will not even want to entertain the idea of looking at photos or videos that are not in color.

I actually think b&w photos are too deceptive. I mean too many people literally picture the world at the time to be black and white. Recall that look is just an artificial limit imposed by immature chemical technology. It’s not like people wanted their pictures looking like that.

It’s even a common trope in modern films to use black and white when showing flashbacks to time periods around the beginning of the 20th century. But that’s not how the world looked! It’s a cheep and deceptive tool imho.

> I actually think b&w photos are too deceptive...Recall that look is just an artificial limit imposed by immature chemical technology.

That limit materially constrained the information that could be captured, but it didn't invent false information. It was a dimensionality reduction from color to simple brightness intensity. Sure, the information captured was through that lens/filter, but there wasn't some AI inventing/guessing at what it was seeing. The photons directly exposed the chemicals in the film. They are not equivalent at all, and your reduction based upon the fact that humans add an additional interpretive perspective to each is a stretch.

I say all of this while being fine with colorized photos, but they should be accompanied by the original photo and the disclaimer that they were colorized. I think colorized photos can add a lot of immersion and trigger emotion, but so does generative, interpretive art.

We shouldn't treat Monet's water lilies as an accurate portrayal of his flower garden at his home in Giverny. Colorized photos, while not as extreme as impressionist paintings, are still a generated piece of art. Perhaps they are more akin to portraits, which have been historically shown bias towards an unflattering view of the subject -- as when they are unflattering, they tend to not to survive[1]

[1] https://en.wikipedia.org/wiki/Sutherland%27s_Portrait_of_Win...

>I actually think b&w photos are too deceptive.

This makes my eyes roll like I'm a professional golfer. I love B&W, and even without using B&W film, I will still turn certain color images I take into B&W. There are lots of artistic reasons, but most of the time it just feels right. Sometimes, it's just an aesthetic reason of matching the decor of where the print is going to hang.

>I mean too many people literally picture the world at the time to be black and white.

So what? There are also people that believe the world is flat. There are plenty of museums full of paintings from well before photography was invented that clearly show color. Anyone that believes that the world was in B&W before color film just need to be walked away from as there's nothing but frustration there.

Well a colorized photo will only be more deceptive since it's just a guess. B&W aren't deceptive, they just are.

B&W photos don't have a lack of color; they've just restricted the color to certain values. A colorized photo might or might not get the colors correct, but the B&W photo definitely doesn't.

Reminds me of an old comic "Calvin and Hobbs" where Calvin's Dad explains why all old photos where black and white.


It’s not entirely fake. These colorization processes exaggerate information about the grayscale tones that our eyes can’t pick up due to subtlety or unfamiliarity with the time, place or people depicted. So while the colorized photos are not entirely faithful, they do tell us more about the scene the photo captured.

> These colorization processes exaggerate information about the grayscale tones that our eyes can’t pick up

It is a machine learning model, so not really.

Instead, the model makes an educated guess of the most likely color, based on vast amounts of pictures sampled un-uniformly from very different areas of the world.

Forgive me for the imprecise language—the bases for the educated guesses are the information I was referring to. Humans are not as good at seeing that a certain shade of gray is more likely to be light yellow than light blue, for example. You’re completely right that datasets trained on regions and historical information would produce more accurate results on black-and-white photos identified to the model as being from similar places and times.

That’s discounting the scores of people who prefer to watch cinema in black and white. Many movies are now coming out with black and white variants (Snyder cut of Justice League, Mad Max: Fury Road etc) black and white isn’t going anywhere. Saying this is like saying people won’t want to read books any more because digital text exists.

I didn't want to look at all the adds on the original page

Never tell someone to not do things like this. If it increases the audience all the better. It's the way people learn things. When you declare things as taboo it only hurts liberty.

There is a valid concern that people may learn/infer wrong things. Liberty isn't end all catch phrase.

People may just as easily infer the wrong things from black and white still photography. There's no defense against people's ability to misinterpret things.

It neat, and works amazingly well. I don't love it though, but I like the look of black and white photos (I was shooting black and white in the 90s when I worked at a college paper). Not having the color in there focuses your attention differently and in my case I would use the camera slightly differently.

But they've alway wanted colors in photographs. Going as far as actually hand coloring them. This is kinda like that but automated.


I wish there was a little symbol you could put in the corner to indicate "colorized" or "altered" for composite photos done with photoshop.

Why? Have you tried just not clicking on the album?

Applications are open for YC Winter 2022

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact