[HN Gopher] This beach does not exist
___________________________________________________________________
This beach does not exist
Author : vsemecky
Score : 205 points
Date : 2021-07-19 09:36 UTC (13 hours ago)
(HTM) web link (thisbeachdoesnotexist.com)
(TXT) w3m dump (thisbeachdoesnotexist.com)
| axiosgunnar wrote:
| Is this the end of stock footage copyright?
| 6gvONxR4sf7o wrote:
| We'll probably end up seeing new IP law to incentivize/protect
| the collection of training data. Creating training data is
| crazy expensive, but exploiting it without
| permission/attribution/compensation is currently legally
| protected as fair use.
| Cthulhu_ wrote:
| One can hope, but I'm afraid it'll only make things more
| complicated.
|
| In theory you could train a generator on stock footage. In
| theory the stock footage copyright holder could sue you for
| creating a derivative work without paying them. In theory that
| claim could be bunkus if the creator used a different training
| set - how do you prove a generated image's origins?
| cocktailpeanuts wrote:
| How would you know which stock photo was used for training?
| Someone may take a whole bunch of images they buy on a dark
| market, create a huge train model, and dump it on the public
| internet over torrent or something. And there would be no way
| to know which images were used to train the model
| laurent123456 wrote:
| Perhaps as this technique becomes more and more used there
| will be regulations on the source data set, such as the
| requirement to prove you own all of it (or that it is in
| the public domain).
| evancox100 wrote:
| Decent case that the derivative work is transformative and
| protected by fair use. (And yes I realize that doesn't stop
| them from suing you, just pointing out)
| dylan604 wrote:
| Would the AI technically own the copyright to the work they
| just produced?
| squarefoot wrote:
| > Is this the end of stock footage copyright?
|
| We probably need ThisMonumentDoesntExist.com for that.
| teekert wrote:
| Just like Co-pilot is the end of the GPL-ed code?
| andrewmcwatters wrote:
| One thing that gets me about GANs is that whatever approach is
| used to generate the outputs always results in GAN-look; these
| images always look "fuzzy" and objects have "hairy" boundaries
| which I suspect is the result of some common gradient function
| technique blending the output in ways that are identifiably
| artificial.
|
| Plenty of photographs have crisp object definitions in the real
| world. These do not. Trees blend into humans standing on the
| beach.
| yakshaving_jgt wrote:
| Plot twist: These are all real beaches but they no longer exist
| because of climate change.
| Minor49er wrote:
| Plot twist: These were all real but don't exist anymore because
| no man can step in the same river twice, let alone swim at the
| same beach
| dredmorbius wrote:
| Plot twist: What is a man? Naked chicken sits in cave
| watching shadows on walls....
| ctoth wrote:
| What a fancy way to wreck a nice beach.
| npilk wrote:
| Does anyone else get extremely powerful uncanny valley vibes from
| these AI-generated images? Even the ones that are pretty good
| give me a sort of deep existential horror.
|
| Actually the original "this person does not exist" wasn't so bad,
| but things like this, DALL-E, or the sheep one that was posted
| the other day I find extremely unsettling and can't explain why.
| unixhero wrote:
| I was going to post the same, but you said it. For me it's
| like; Then if this can "not-exist" now, we're at level already.
| We're approaching a "what is real situation", should we be able
| to put this into a person's memory.
| tokamak-teapot wrote:
| Absolutely. I've been wondering if noticing that 'something
| feels wrong' is a deeply ingrained response related perhaps to
| survival. When a possible threat is detected, even when it's
| not clear what the threat is, it's time to feel very
| uncomfortable.
| phkahler wrote:
| >> Absolutely. I've been wondering if noticing that
| 'something feels wrong' is a deeply ingrained response
| related perhaps to survival.
|
| I thought the latest thinking is that most of what we "see"
| is really a projection from our own mind (similar to how
| these images are generated) and our attention is drawn to
| those areas where our projection and sensory input don't
| match. So yes, we are evolved to be alerted when "something
| feels wrong" because it's unexpected and could be a danger.
|
| The mismatch can happen at any level of the hierarchy. One
| person here said some waves appeared to be moving the wrong
| way for the rest of a scene. Things like that are at a higher
| level of abstraction than rock textures or tree trunks with
| gaps. Some things might seem wrong but take more time to
| identify or explain what the problem is.
| seph-reed wrote:
| Most of human comfort (which isn't pharmaceutically induced)
| comes from a sense of familiarity. Unfortunately, this is
| also where most people get their sense of "truthiness," but
| that's another story.
|
| Anyways, if you were raised in a machine with these images
| and then shown the real world, I wonder if it would be a
| relief or also uncanny?
|
| I know that when it comes to sound, it's really hard to
| create organic sounds. And that part of our ability to hear
| sounds happens (theoretically) before the brain, in the form
| of grouping harmonic series together into isolated sound
| sources. Perhaps eyes do something similar? Some sort of pre-
| processing that functionally works for all natural phenomena,
| kind of like the harmonic series does for sound.
| qqqwerty wrote:
| Yes, I had to close the page after about 5-10 seconds of
| browsing. Interestingly, I have been slowly cutting back on
| coffee and am a bit sluggish as a result, but after looking at
| those images my mind got a bit of jolt.
| sizzle wrote:
| Wonder if you activated a fight or flight response
| spike021 wrote:
| Interesting work. I wish the video paused on at least some of the
| beaches though so you can actually look at them before they
| transform into the next one.
| sdflhasjd wrote:
| When they do these "Random Latent Walk" animations, it becomes
| apparent that some features sort of... stay still (i.e the detail
| in the leaves seems to not actually move, but the larger features
| such as branches move _around_ it)
|
| Does this artifacting have a name?
| soraki_soladead wrote:
| This problem was recently addressed in detail here[1] which
| serves as a good overview.
|
| 1. https://arxiv.org/abs/2106.12423 (project page:
| https://nvlabs.github.io/alias-free-gan/)
| moron4hire wrote:
| Holy... ! That second video, the character on the right, one
| of her incisors ends up in the middle of her mouth. It's
| amazing how these things can get so many details right, just
| from analyzing existing images, but some details like the
| symmetry of teeth get lost.
| steelframe wrote:
| Long-shot request: Generate 3D models of beaches like this for a
| flight simulator.
| bencollier49 wrote:
| There's a character in "Soylent Green", an old fellow who claims
| that there used to be all sorts of wonderful nature back in the
| past, but no-one believes him. I feel like this stuff could
| facilitate a similar situation.
| darkwater wrote:
| In some of these pictures [1][2][3] the vegetation and the rocks
| look like if they had been "photoshopped" by some amateur. Anyway
| it's a great start for sure!
|
| [1] https://thisbeachdoesnotexist.com/data/seeds-075/4375.jpg
|
| [2] https://thisbeachdoesnotexist.com/data/seeds-075/3300.jpg
|
| [3] https://thisbeachdoesnotexist.com/data/seeds-075/7638.jpg
| Pxtl wrote:
| Yeah, the texture on the rocks in [3] look more like the animal
| hide of a giant animal like an elephant or a rhino than they do
| stone.
| AndrewOMartin wrote:
| Do these projects ever have a way to ensure the output isn't just
| one of the elements of the training set? Is it simply something
| that would be of negligible probability of happening?
| atorodius wrote:
| Typically they would investigate something like the closest (in
| terms of eg MSE) image from the training set.
| IdiocyInAction wrote:
| MSE is kind of crappy for images; you'd use something like
| image-specific, like SSIM.
| jstx1 wrote:
| How do you compute MSE between images?
| unoti wrote:
| How to get MSE between images:
|
| 1. Express each pixel as a vector of numbers, probably with
| RGB.
|
| 2. For each of the color vectors, for each of the colors,
| subtract the color 1 from color 2.
|
| 3. Square those differences, and add them.
|
| In this way you can get mean squared error for each pixel
| or for the entire image.
| jstx1 wrote:
| Right but I don't see how it's useful in this context
| given that rotations, reflections and translations of an
| object across the canvas can give you high MSE while
| retaining most of the original image.
| Yajirobe wrote:
| How do you know it really does not exist? There is this effect
| called 'over-fitting', where you might expect an exact sample
| from the training set to show up in the video
| cunthorpe wrote:
| The video made me seasick
| username91 wrote:
| The video on the site is very enjoyable to have on in the
| background at 0.25x speed.
| dylan604 wrote:
| It's like one of those sci-fi time travle movies or docuseries
| showing the evolution of the earth/techtonic plates/etc.
| licebmi__at__ wrote:
| As someone who is terrified of the deep sea (caused probably by
| Lovecraft's work), I find the artifacts on the images truly
| unsettling.
| dvh wrote:
| I recognize some photos from pexels(dot)com, they are all public
| domain.
| moron4hire wrote:
| NVidia has some interesting developments in this vein,
| specifically with temporal coherence so subsequent frames of
| animation are consistent over time:
| https://www.youtube.com/watch?v=jl0XCslxwB0
| systematical wrote:
| The rocks are really bad
| dredmorbius wrote:
| Rock is dead, they say.
| stolenmerch wrote:
| Would love to see some blind study on what people actually find
| "uncanny" vs. what they think is uncanny because they are told
| it's a generated image. Maybe I don't fully understand the
| concept of the "uncanny valley" but simply saying This Looks
| Shopped isn't uncanniness.
| moron4hire wrote:
| The problem with that is that the very definition of "uncanny"
| is that it is subjective. You see it and feel that it is off,
| without being able to explain why.
| srg0 wrote:
| I think that these images are less convincing than
| "thispersondoesnotexist". The network did well for the extent a
| tree is similar to a person: long palm leaves look are like green
| hair, and look passable.
|
| The network did bad where it had to take into account global
| illumination, or distance to the object and its level of detail:
| 1) tree trunks are mostly flat and do not depend on the possible
| sun location; 2) shadows don't match the trees and the rocks; 3)
| nearby rocks often lack texture and are not properly illuminated
| (they look flat).
|
| It's not surprising given that the method is fundamentally local
| (CNN-based). I think better results will be achieved when a
| generator creates a scene graph rather than a raster. Are there
| works which actually create a 3D scene (or use it as an internal
| representation)?
| andrewmcwatters wrote:
| Given that these scenes are produced from existing rasters, I
| don't know how you would do that without either data
| classification or time of day/GI inference. You'd have to do
| spacial inference to produce the 3D scenes which is more
| complicated, and then at that point if you're using the
| generated raster output as textures, you'd have to normalize
| them to their albedos and then do global illumination from
| there.
| amelius wrote:
| I'm waiting for a "this X does not exist" website generator.
| pantulis wrote:
| "This GAN does not exist"
| dredmorbius wrote:
| This GAN _could not_ exist.
| facethewolf wrote:
| "This this x does not exist does not exist"
| whymauri wrote:
| I was actually thinking about the details of implementing this
| after reading the title.
| scubbo wrote:
| Same :) seems like you could get pretty decent results just
| selecting random nouns?
| whymauri wrote:
| I would like to also couple an algorithm to generate those
| images. Maybe just randomly select nouns for the title, but
| pass on augmented/cleaned versions of the title to some
| generator + CLIP to autogenerate fitting images.
| egfx wrote:
| It used to be called stumbleupon.
| cltsang wrote:
| "This website does not exist"
|
| recursion paradox joke :)
| optimalsolver wrote:
| My favorite of these is This Chemical Does Not Exist:
|
| https://www.thischemicaldoesnotexist.com/
| gus_massa wrote:
| Nice!
|
| Only a small feature request: When you click the button to get
| another set of random images or another cluster in the knn, the
| page waits until the new image is loaded to update it, so it
| "does nothing" for half a second. I'd like that it instantly
| shows a spinning thing or other signal to show that it's waiting
| for info and will be updated soon.
| vsemecky wrote:
| Launching a new hobby deep learning project
| https://ThisBeachDoesNotExist.com - a synthetic beach image
| generator built on a neural network StyleGAN.
| GistNoesis wrote:
| Is this a ShowHN ?
|
| It looks nice, but I don't feel safe using untrusted pickle
| weights of pretrained models, as they can allow for arbitrary
| code execution.
| vsemecky wrote:
| Probably yes, although I'm not sure I understand exactly what
| ShowHN is.
|
| I fully understand your concerns, but I don't know how to
| guarantee that the pkl is ok. Don't run it on your computer,
| but in some isolated environment, like Colab.
| im3w1l wrote:
| The solution is to use a different format that is safer.
| GistNoesis wrote:
| https://news.ycombinator.com/showhn.html
|
| I'd argue that running untrusted code in a Colab is even
| worse, as you'd risk your account instead of just your
| computer.
|
| I don't think pickle files can be loaded safely, it's
| better to use a numpy archive npz to store the weights
| which can be loaded without a security risk by using
| allow_pickle=false when loading (the default since numpy
| 1.16.3)
| marcodiego wrote:
| I'd say these images have high artistic value. In the coming
| years it is very likely that "real art" will be confined to snobs
| and most people will be able to buy non series produced high
| quality automatically generated art.
| Touche wrote:
| I've never understood the appeal of photorealistic art anyways,
| so I'll be happy to be labeled a snob that likes art that looks
| like art.
| andrenotgiant wrote:
| I agree, I think most photorealistic art lost most of its
| appeal when color photography came out.
|
| Maybe there's a brief moment of "I'm impressed with how much
| work you put into this" but for that to happen, you kind of
| have to see the work being done.
|
| I think that's why impressionism has such staying power,
| impressionists realized that your brain doesn't need
| photorealism. They were panned by their contemporaries who
| were focused on photorealism, but time has proven they were
| onto something.
|
| Even now the impressionist-style neural nets don't get it
| right.
| vharuck wrote:
| >Maybe there's a brief moment of "I'm impressed with how
| much work you put into this" but for that to happen, you
| kind of have to see the work being done.
|
| Or be knowledgeable enough to estimate the effort and skill
| required. Ironically, things I took for granted when I was
| young have impressed me more and more over the years.
| Probably because I've either tried to do them myself or
| learned about their backgrounds.
|
| So I'm not surprised artists and at enthusiasts would value
| realism more than most people. Just like how speed metal is
| probably more popular among guitarists. The technique
| becomes a source of value rather than just an
| implementation detail.
| Touche wrote:
| I'm an artist that doesn't like photorealism. I can
| appreciate the skill without wanting to spend much time
| looking at it. The imperfections and accidents are what
| make art pieces interesting to me.
| rob74 wrote:
| Nice effort, but as with all these "this X does not exist" image
| generators, it gives you an uncanny feeling. Something about some
| of the images is slightly off, but you (or at least I) are not
| able to put your finger on it most of the time. One of the things
| I _was_ able to put my finger on are the palm trees - some of
| them have leaves hanging in mid-air...
| gpvos wrote:
| Or entire trees...
| bradrn wrote:
| For me, what really stood out were the rocks -- real rocks just
| don't have those sorts of textures.
| BitwiseFool wrote:
| I thought they looked great at first but as soon as I started
| taking a closer look, everything started to look very wrong.
| I'm certain growing up near an ocean gave me a more critical
| eye.
| dylan604 wrote:
| I was hoping to see something like in Contact where everything
| looks normal except something is weird. They made the waves run
| in reverse so they appear to be originating from the beach.
| samkater wrote:
| Agreed on the nice effort comment. The ones showing the scene
| from a distance took me some extra time to figure out what was
| "off". For me it is the whitecaps on the water (if present).
| Some of the pictures appear to show waves going in the opposite
| direction of their surroundings. One of those things that when
| you see it, you can't really unsee it.
| brandnewlow wrote:
| Can you share links to some others of these?
| dougSF70 wrote:
| Surely, the title should be the "photo of this beach does not
| exist". Beach photos are always a bit samey so it is probably
| more straight forward to train AI to build a random beach photo
| than to actual build a map of a beach.
___________________________________________________________________
(page generated 2021-07-19 23:02 UTC)