You mention black and white colorization and that was my first thought upon seeing this. The statues are already super “photo-realistic” so I’m guessing this was a pretty similar process.
On a completely different note, I am not sure what you’re getting at with the racial stuff. Like what are you suggesting? That perhaps some of the emperors weren’t totally Caucasian but rendering them as such from the best available evidence is somehow racist? In my humble opinion, trying to find racial undertones in every tangential thing is a distraction from the real conversations that we should be having. And there’s a real possibility of alienating people that are otherwise sympathetic to the cause.
> On a completely different note, I am not sure what you’re getting at with the racial stuff
What I am saying is that this sort of work can lead to people believing these images as true, i.e. "this is what Roman Emperors looked like". If you ask an ML system to solve a problem for which the inputs cannot possibly determine the answer (i.e. the color of a fossilized animal or the skin color from a person's statue), it will give you a highly biased answer.
I fear that some laypeople think of ML as "magic software that can do anything" without considering whether a problem is non-ambiguous given its inputs (e.g. something like object classification is less ambiguous than this problem).
I'm not saying "burn it to the ground" - I wanted to learn more about what data and model was used to generate these images so that I might understand better where potential sources of racial / ethnographic bias might come from.
> trying to find racial undertones in every tangential thing
If you read my comments history you'll see that I'm no critical race theorist, nor do I discuss everything in a racial context.
Out of curiosity, what "cause" are you talking about?
I agree. I think the problem very much starts with the sculptures themselves. It seems rather likely that the sculptors would have had an incentive to "improve" some of the not so attractive features of those very powerful men.
A realistic ML model could theoretically compensate for that by reintroducing a bit of variability based on the variability we see in today's population of that region.
On the attractiveness point, the author mentions that in the case there were multiple visual sources, the one which would likely be considered less attractive was chosen. (Under the assumption that it was probably more accurate since as you stated, there was likely incentive for flattery.)
It certainly hasn't remained exactly the same, but there could be quite a bit of similarity left:
It is generally agreed that the invasions that followed for centuries after the fall of the Roman Empire did not significantly alter the local gene pool, because of the relatively small number of Germanics, or other migrants, compared to the large population of what constituted Roman Italy.
In 2008, Dutch geneticists determined that Italy is one of the last two remaining genetic islands in Europe, the other being Finland. This is due in part to the presence of the Alpine mountain chain which, over the centuries, has prevented large migration flows aimed at colonizing the Italian lands[1]
The migrants comprised war bands or tribes of 10,000 to 20,000 people,[5] but in the course of 100 years they numbered not more than 750,000 in total,[citation needed] compared to an average 40 million population of the Roman Empire at that time.[2]
The same can be said of the original advanced technology used to render a facsimile of the Roman Emperors, and in fact .. many stone sculptors have lost their prestige for the sake of this very same argument.
Since culture is a lie which persists only in the telling, this IS what the Roman Emperors look like, now. You shouldn't resist that, because there is no truth on this issue, anyway.
Is there anything in the HN guidelines about willfully dismissing or obscuring the truth? This comment makes me feel like there should be.
Saying "we'll never know anyway so stop asking" is abhorrent to me, and I imagine many on this forum. Not to mention it aims to end a discussion it doesn't understand.
Well, the sculpture is a fiction, and this AI generated image is a fiction - what's wrong with acknowledging that these fictions are all we have? Life is a collection of these facsimiles.
Acknowledging that is fine. Saying that makes further conversation irrelevant moves us in the wrong direction as a society.
Money is a fiction, history is a fiction, most scientific concepts eventually become fiction at a low enough level. And look at the world we've built on top of those fictions. It may not be perfect but it is undeniably meaningful.
You'll never know with certainty, but you can certainly know more than you do now. But you won't if you don't pursue the truth, and it becomes a self fulfilling prophecy. As I said in another post, maybe it's possible to sequence DNA of the emperor or a collection of contemporary subjects, determine an approximate ethnic makeup, and revise the images based on that.
Or, we can just assume we are already correct because we'll never know anyway.
I don't think the parent comment was saying "stop asking" merely that "the answer is unobtainable, so any discussion about it is going to be grounded on that"
> trying to find racial undertones in every tangential thing
In this case it isn't tangential but central, since the point is extrapolating physical appearance from incomplete data. It matters if the results predict inaccurate racial features because plenty of people unfortunately care about kind of thing.
And remember that laypeople read "researchers used machine learning" as "super smart people used advanced science to get this result so it's probably true."
I feel like the current climate of society shows that people who have such a simplistic view of science don't tend towards "smart people said this, so it must be true"....
It is, but the criticism is that it's easy to misunderstand and/or skip over the "incomplete" part, and get a wrong conclusion that the results are more accurate than they actually are.
My understanding of the original point is that ML models are trained on a data set. If you train the model on a data set that is only made up of white faces, the results will be whiter than if you train it on a data set that is made up solely of black faces. They said they'd like to know the makeup of the data set that the model is trained on to more fully understand how the results were produced.
> That perhaps some of the emperors weren’t totally Caucasian but rendering them as such from the best available evidence is somehow racist?
These days, sadly, yes. The definition of racism has been so diluted in recent years that, as you implied, I fear it's often a distraction from actual racial injustice. Anyone ever hear of the boy who cried wolf?
I don’t think gp was implying rendering as such to be racist, but was more concerned about people taking these renders as fact and using them to justify a prejudiced world view.
If someone is prone to accepting the idea that caucasians are superior to others they may use something as seemingly innocuous as this neat project to justify their positions and the lack of disclaimers towards the inaccuracies of certain aspects of these renderings may do a small harm societally.
On its own it’d be fine but in conjunction with other symbols and narratives it can become part of a larger, more sinister narrative.
The "racial stuff" seems relevant here. Sure, some people try and insert race into everything, but in this case it's a relevant, and interesting aspect of the problem domain.
My understanding is that the racial identity of the ancient Romans are actually a lot more ambiguous then most people realize, and the way the author attempts to reconcile that ambiguity has a huge impact on the image output here. And it's an interesting problem, Yann LeCun has discussed a bit about how to account for racial diversity via ML techniques (it's not just about the training data set!).
From what I recall, the reason for this racial ambiguity is because ancient Rome (and the entire Mediterranean region) was a cosmopolitan hotbed where many different ethnicities were mixing together all the time. On top of that, they didn't have the same kind of racial constructs we had, and so it's actually unclear what the races of various ancient Romans actually were.
The way I like to explain it to people is that culture, ancestry, and language are 3 separate (but related) things. Knowing one doesn't necessarily tell you anything about the other two. In this case, it would tell you that the genetics are not sufficient to describe the categories of Roman ethnicity without additional justification that in this one particular case, they are.
Colors are can be subjective and somewhat politicized even when there's a written description. It's kind of like how every culture tends to color Jesus to be more similar to the local people, even though everyone knows he's from the middle east.
I might call someone blond with blue eyes, but someone else might describe the same person hair with light brown with green eyes. If we had third person choose which colors represented the descriptions, they might pick completely different colors based on what they thought blond or light brown meant.
Caligula looks to be on point based on the restoration of his original colors in that article.
To your second point, that reminded me that Japan's traffic signals use a different color "green" (looks more blueish) than the rest of the world and they have a common, named color that doesn't really map to blue or green in the rest of the world: https://en.wikipedia.org/wiki/Ao_(color)
These images were rendered with a "white" bias. Facial features is one thing, but skin color is clearly not conveyed by statues, yet a clear choice was made here.
Is that not what 'blonde' generally is in adults? An image search for 'blonde man' returns men I'd consider 'blonde' which hair which seems objectively light brown (except those with obviously bleached highlights.)
The color of Augustus here[0] is definitely blonde for me, bordering on platinum, while what I meant is that it might as well have been darker, i.e. [1] which I would call "light chestnut".
It doesn't matter. Non-white people without steppe ancestry are pretty much uniformly dark-haired and don't have names akin to "subflavum" for traditional hair colors, because light yellow/gold hair just isn't a thing, regardless of what exactly they conceive of as "yellow/gold".
You can't just claim this without suggesting what's actually wrong. What is wrong, and where are the good sources from which we can make a comparison? If you're just guessing then you're no better than this ML model.
On a completely different note, I am not sure what you’re getting at with the racial stuff. Like what are you suggesting? That perhaps some of the emperors weren’t totally Caucasian but rendering them as such from the best available evidence is somehow racist? In my humble opinion, trying to find racial undertones in every tangential thing is a distraction from the real conversations that we should be having. And there’s a real possibility of alienating people that are otherwise sympathetic to the cause.