Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

This Sneaker Does Not Exist

thissneakerdoesnotexist.com

Post reply on HN
Print view View original

21–30 of 72 posts

Re: This Sneaker Does Not Exist

#21

Post by StanvdVossen »

injidup wrote: post #11
StanvdVossen wrote: post #7

Earlier quoted context omitted.

That's definitely a cool idea! I might ask around different webshops to see if they're interested in something like this.

Too many of those shoes look like they have a munged Nike logo which means that any company trying to ship them would soon be receiving a kindly call from the Nike megacorp lawyers. You would have to improve the training to avoid generating trademark / logo infringing designs. Could this be trivially done?

In general this would not be easy.

One way this can be accomplished is by removing all shoes with such logos from the training data. But Nike and Adidas are disproportionally large parts of my training set, so this would not be feasible.

The other option would be to train a machine learning model to recognize said logo's and to use this model to remove sneakers with logo's from my generated images. This could however greatly reduce the variety of images on the website.

Re: This Sneaker Does Not Exist

#22

Post by piva00 »

StanvdVossen wrote: post #17
5350-uiop-1130 wrote: post #15

maybe i'm oversimplifying. i had the same thought about the "thispersondoesnotexist" site...but are these not just composites of things that do exist? or maybe that's the point.

You’re somewhat right. The machine learning algorithm tries to replicate the general patterns on the images it’s trained on (so in this case, images of a lot of sneakers). If the algorithm is trained on enough images, it should, to an extent, learn to generalize and “understand” what a sneaker should look like and generate new ones rather than copying images. In my case, there is definitely some memorization going on…

As a bit of a sneaker head, it's been quite fun to see how the algorithm changes the shapes when playing with the sliders on the Sneaker Editor.

Impressive that it isn't copying/pasting parts of shoes but actually building them pixel-by-pixel, I was editing a very AF1-looking sneaker and playing with the sliders made actual sensible changes to the shape and design.

Pretty entertaining :)

Quick edit: as a side question, the training dataset included all kinds of sneakers or was it biased towards more popular ones? I ask because from what I scrolled I missed seeing more avant-garde designs and wasn't sure if the model was trained on these or not.

Re: This Sneaker Does Not Exist

#23

Post by jstx1 »

I get that the title is in the theme of this-x-does-not-exist but I don't think it's true in this case. Many of these look like existing models.

The amount of variation in sneakers is limited so when you have 50k training images you end up copying some of them with little to no change because if you deviate too much you end with something that doesn't pass as a sneaker at all.

Re: This Sneaker Does Not Exist

#24

Post by soulmerge »

injidup wrote: post #11
StanvdVossen wrote: post #7

Earlier quoted context omitted.

That's definitely a cool idea! I might ask around different webshops to see if they're interested in something like this.

Too many of those shoes look like they have a munged Nike logo which means that any company trying to ship them would soon be receiving a kindly call from the Nike megacorp lawyers. You would have to improve the training to avoid generating trademark / logo infringing designs. Could this be trivially done?

I don't think that is an issue: The process should just help the user find the right shoe. If the user repeatedly picks shoes with a logo, he will be presented shoes of that brand, that the vendor has in stock. This is actually beneficial to the trademark holder.

Re: This Sneaker Does Not Exist

#25

Post by soulmerge »

jstx1 wrote: post #18
soulmerge wrote: post #6

Wow, I think this would be pretty useful as a shopping guide in an online shop: Let the user pick a few models they like and render more items based on the chosen ones. Present actual sneakers you have in stock at the last step.

Maybe I'm not getting it. What's the benefit of showing people the imaginary sneakers? Why not show them what they can actually buy?

I think the experience is more like an employee coming to you and asking you what you're looking for in a shoe, instead of entering an empty store and browsing all available shoes. I would certainly prefer some guidance, as I usually have no clue what I'm looking for.

Re: This Sneaker Does Not Exist

#26

Post by fxtentacle »

jstx1 wrote: post #23

I get that the title is in the theme of this-x-does-not-exist but I don't think it's true in this case. Many of these look like existing models. The amount of variation in sneakers is limited so when you have 50k training images you end up copying some of them with little to no change because if you deviate too much you end with something that doesn't pass as a sneaker at all.

In most cases, GAN produces a random mixture of features extracted from real photos. That's also why you can tempt GitHub Copilot to regurgitate Carmack's swearing comment.

Re: This Sneaker Does Not Exist

#27

Post by FeepingCreature »

fxtentacle wrote: post #26
jstx1 wrote: post #23

I get that the title is in the theme of this-x-does-not-exist but I don't think it's true in this case. Many of these look like existing models. The amount of variation in sneakers is limited so when you have 50k training images you end up copying some of them with little to no change because if you deviate too much you end with something that doesn't pass as a sneaker at all.

In most cases, GAN produces a random mixture of features extracted from real photos. That's also why you can tempt GitHub Copilot to regurgitate Carmack's swearing comment.

Sufficiently advanced random mixture of features extracted from real photos is indistinguishable from genuine understanding.

That's why I don't understand this argument. It's not true - you can make the AI generate specific samples, but most samples can not be found in the training data - but even if it was true, it wouldn't prove anything anyways, because you can always say "well the features it copies are just smaller" until the features are just combinations of pixels. It's unfalsifiable even for human artists.

Re: This Sneaker Does Not Exist

#28

Post by jstx1 »

fxtentacle wrote: post #26
jstx1 wrote: post #23

I get that the title is in the theme of this-x-does-not-exist but I don't think it's true in this case. Many of these look like existing models. The amount of variation in sneakers is limited so when you have 50k training images you end up copying some of them with little to no change because if you deviate too much you end with something that doesn't pass as a sneaker at all.

In most cases, GAN produces a random mixture of features extracted from real photos. That's also why you can tempt GitHub Copilot to regurgitate Carmack's swearing comment.

The usefulness of any of this generated stuff eludes me.

Re: This Sneaker Does Not Exist

#29

Post by StanvdVossen »

piva00 wrote: post #22
StanvdVossen wrote: post #17

Earlier quoted context omitted.

You’re somewhat right. The machine learning algorithm tries to replicate the general patterns on the images it’s trained on (so in this case, images of a lot of sneakers). If the algorithm is trained on enough images, it should, to an extent, learn to generalize and “understand” what a sneaker should look like and generate new ones rather than copying images. In my case, there is definitely some memorization going on…

As a bit of a sneaker head, it's been quite fun to see how the algorithm changes the shapes when playing with the sliders on the Sneaker Editor. Impressive that it isn't copying/pasting parts of shoes but actually building them pixel-by-pixel, I was editing a very AF1-looking sneaker and playing with the sliders made actual sensible changes to the shape and design. Pretty entertaining :) Quick edit: as a side questio…

Thanks!

The training set included pretty much all sneakers I could find online. However, the algorithm tends to bias towards patterns that are more common e.g. hundreds of colorways of Air Jordans.

BUT I can fine tune the model by training on a small subset of sneakers. So if you have any types of brands or sneakers that you would like to see generated, please feel free to mail me some examples at stan@thissneakerdoesnotexist.com and I will see what I can do.

Re: This Sneaker Does Not Exist

#30

Post by prawn »

mosselman wrote: post #14

There are some very nice designs in there. I bet you could start a legit brand or 5 with some of these in the catalog.

Generate 1,000 designs. Run them through a hot-or-not or a-vs-b competition. Make the winning sneakers into actual products.
Post reply on HN