[HN Gopher] The emergence of full-body Gaussian Splat deepfake h...
___________________________________________________________________
The emergence of full-body Gaussian Splat deepfake humans
Author : Hard_Space
Score : 85 points
Date : 2023-12-15 10:49 UTC (12 hours ago)
(HTM) web link (blog.metaphysic.ai)
(TXT) w3m dump (blog.metaphysic.ai)
| bondarchuk wrote:
| > _Since the advent of Gaussian Splats, in August of this year,
| the image synthesis research community has clearly embraced this
| innovative approach to neural recreation of people, things and
| scenery._
|
| I thought splats were explicitly _not_ neural?
| danbruc wrote:
| I also find their usage of the word neural very confusing but
| this is how they explain it.
|
| _A Gaussian Splat, instead, is a neural_ representation unit
| that is not limited in this way - not only can it be assigned
| anywhere in XYZ /3D space, but it can as necessary multiply and
| subdivide into additional splats, as coverage requires.*
|
| And the asterisk leads to the following explaination.
|
| _Technically it's a rasterization unit rather than a neural
| unit, but in all current Splat implementations that are of any
| power or interest to the synthesis community, it ends up as a
| neural unit, passed through standard training processes.
|
| Amended Friday, December 15, 2023 13:33:47 EET to clarify
| 'neural unit'_
|
| But even with this I am not sure that I understand what they
| want to say.
| lainga wrote:
| > But even with this I am not sure that I understand what
| they want to say.
|
| Look at the domain name of TFA. They are saying "neural
| neural PageRank look at meeee"
| sorenjan wrote:
| What does neural mean nowadays anyway? I thought neural nets
| got their name from the perceptron's resemblance to
| interconnected neurons, but what about CNN's or transformers?
| From what I can tell neural just means "plenty of parameters
| optimized using a learning process", in which case gaussian
| splats fits the description.
|
| I also think gaussian splats encode the same information as
| NeRFs, which have neural in the name.
| throwup238 wrote:
| I thought neural meant df/dx optimization applied to a giant
| function.
| bondarchuk wrote:
| > _but what about CNN 's or transformers?_
|
| They also consist (in the abstract, at least) of
| interconnected neurons with activation functions.
| numpad0 wrote:
| Anything that require cuDNN installed in dev environment.
| danbruc wrote:
| _[...] plenty of parameters optimized using a learning
| process [...]_
|
| Would that not make fitting a degree 1,000,000 polynomial a
| neural method?
|
| _I also think gaussian splats encode the same information as
| NeRFs, which have neural in the name._
|
| The collection of source images also encodes the same
| information but I don't think we should call them neural
| images.
|
| I would argue we should stick with the original meaning,
| inspired by biological neural networks, a network of
| artificial neurons. Calling everything neural because of the
| hype will benefit no one in the long run as the term will
| just lose any meaning.
| hansvm wrote:
| Practically speaking, it's a history-dependent definition.
| Some set of things are considered "neural", somebody makes an
| innovation that's based on the existing set of "neural"
| tools, and now the set of "neural" things is expanded to
| include the new innovation.
|
| For this post, they have more traditional neural networks
| embedded in the pipeline (search TFA for "decoder"), and
| they're thus calling the composite technique a "neural"
| technique.
|
| As to the CNN/Transformer/... question, those are still very
| similar to a perceptron. A multi-layer perceptron has a
| sequence of alternating matmuls and activations. The CCN has
| a particular choice of sparse matmul and activation (and a
| couple choices of fast implementations to operate on that
| sparse matmul). A Transformer is one way to wire up many such
| MLP predictions (recurrent networks being another) to work
| with long/uneven inputs. There's more going on, but most of
| it is fluff to make the thing numerically stable and do
| something interesting. The core structure is still a dressed-
| up perceptron.
| elif wrote:
| I'm sure the primary use case of this technology is in film.
| (e.g. Disney populating background extras)
|
| But I would LOVE to see this transformed into a game engine/game
| dev IDE. Imagine if anyone with a smartphone could create
| photorealistic character models in under a minute. Hell, players
| could even provide themselves as character models ad-hoc without
| involving any devs.
|
| It would be a renaissance moment for game development speed and
| accessibility, and make things like 'asset store games'
| irrelevant.
|
| Imagine an LLM built to understand a base game engine template
| code, and also able to perform gaussian splat transformation on
| frames of input video.
|
| It also seems like it could be the missing link for AR/VR
| crossing the uncanny valley.
| sorenjan wrote:
| Lets hope the primary uses are entertainment and maybe
| communication. It will soon be possible to create a realistic
| video of anyone doing anything.
| numbsafari wrote:
| Which is why we need laws that make doing so without very
| explicit consent for every generated work a felony offense
| with social and penal consequences equivalent to rape.
| sorenjan wrote:
| That won't help against nation states spreading propaganda
| or manufacturing false evidence. If you thought Russian
| Twitter trolls were bad in 2016, wait until you see the
| TikTok trolls of tomorrow.
|
| This won't be regulated away, it will happen and everyone
| should be educated and prepared. That's just an unrealistic
| dream though, enough people will get fooled (I will
| probably be among them at least some of the time) that it
| will have consequences. Deepfakes have been used for scams
| for years already:
| https://www.youtube.com/watch?v=vqr0oER03SE
| numbsafari wrote:
| Murder isn't regulated away, either. Yet it is still
| against the law, and society invests in its prevention,
| and empowering the victims of violence with a civil means
| to seek retribution and protection.
|
| The situation is very similar to CP, and should be
| treated in a similar fashion.
| positus wrote:
| An abundance of laws is little help against the evil
| intentions of the human heart.
| numbsafari wrote:
| It would give victims a path to defend themselves. Today,
| they have nothing.
| semiquaver wrote:
| Deepfake videos aren't covered by existing libel law?
| numbsafari wrote:
| To the best of my knowledge, in the US, there is no
| explicit law and libel/defamation laws have not been
| adequately tested and it is understood that they have
| very serious limitations, especially for those who
| previously engaged in sex work.
|
| > But no federal law criminalizes the creation or sharing
| of non-consensual deepfake porn in the United States. A
| lawsuit is also unlikely to stand up in civil court.
|
| https://www.wbur.org/endlessthread/2023/06/23/deepfake-
| porno...
|
| > ... if someone makes a deepfake or otherwise posts a
| nonconsensual video of someone who does sex work, the
| defense could argue that because the woman's reputation
| already involves sexual activity, her reputation is not
| being defamed by another video of sexual activity. Such
| an argument -- and thus pursuit under defamation as a
| whole -- would be missing the actual point, which is the
| violation of consent.
|
| https://www.cyber.forum.yale.edu/blog/2021/7/20/deepfake-
| por...
| Aardwolf wrote:
| Would it be too optimistic to say that if we can create
| realistic videos of anyone doing anything, the general public
| will not believe in videos as evidence anymore anyway? And so
| it wouldn't matter soon, except it would matter for a
| different thing, namely we'll lose the ability to use legit
| videos as evidence of anything.
|
| On the other hand, it has been possible for an extremely long
| time (millenia) already to create text of anyone doing
| anything, and in general it seems we can still trust text
| mostly (and can distinguish somewhat well between false and
| reputable textual sources), so maybe it's all reputation
| based, also for video in the future.
| Podgajski wrote:
| I could also see government agencies using this to frame
| people for crimes they do not commit.
| danielbln wrote:
| Thanks to insightface anyone can already deep fake any
| video with a single input image in a few seconds.
| andyjohnson0 wrote:
| > I'm sure the primary use case of this technology is in film.
| (e.g. Disney populating background extras)
|
| If the recent history of tech is anything to go by, the most
| popular in-practice use case will be porn. All it will need is
| a corpus of training data: which it's safe to assume already
| exists.
|
| After that, deepfaking $WorldLeader$ doing something
| embarrassing is probably #2 or #3. Just in time for the US
| elections...
| hugh-avherald wrote:
| I had a friend who worked in the Treasury Department and got
| access to government decisions and statistics releases before
| the general public did. He and his team would often make
| paper trades to try to guess the effect of these decisions.
| They were surprised how often they lost money.
|
| I suspect in the upcoming election, deepfaking the candidates
| doing something out-of-character would have a similar
| surprising effect.
| dzink wrote:
| Political deep faking may be seen during elections, but
| imagine if someone faked corporate executives acting poorly
| to subvert/short stock prices. The sky is the limit on
| abuse.
| api wrote:
| People will have to learn that nothing can be believed no
| matter the medium unless there is a verifiable chain of
| custody to the information.
|
| This is the way it always was back when our primary means
| of communication was verbal and hand written. Everyone
| knew anyone could lie. We then had this bizarre period of
| time when you had certain types of media, especially
| photographs and video, that were extremely hard to fake
| convincingly. That period is now over and we have
| returned to the norm: you can't believe it unless the
| provenance of the information is known and the chain of
| custody is trustworthy.
|
| This needs to be drilled into people starting in
| elementary school.
| irrational wrote:
| > the chain of custody is trustworthy
|
| This seems like the hard part. How do I know that
| anything anyone is sharing is trustworthy? It's not like
| I'm going to trust any news org, government, non-profit,
| corporation, anonymous individual, etc.
| KittenInABox wrote:
| How do we verify/trust chain of custody of, idunno, "Mark
| Zuckerberg calling for the killing of all lefthanded
| people"?
|
| What I think will happen is that it'll be like what we
| have now but worse: some podcaster will make an offhanded
| remark about Mark Zuckerberg "saying some horrible stuff
| about lefthanded people" causing frantic TikToks about
| that it means killing lefthanded people, all based on a
| supposed "secretly recorded video" that no one can
| validate due to all of the noise.
| Podgajski wrote:
| And the other side of this coin now is that people can do
| truly horrific things that can dismissed as created by
| AI.
| bryanlarsen wrote:
| Back in that era (and continuing today) rumours were
| routinely believed and significant harm was done via
| rumour.
|
| Convincing people that photos and video are as believable
| as a rumour is not as helpful as it should be.
| CamperBob2 wrote:
| _Convincing people that photos and video are as
| believable as a rumour is not as helpful as it should
| be._
|
| It is very helpful to some people, namely those parties
| who flourish among the ignorant and poorly-educated.
| Remember that the real goal of disinformation isn't to
| make you believe false things; it's to make you believe
| _nothing_.
| tivert wrote:
| > People will have to learn that nothing can be believed
| no matter the medium unless there is a verifiable chain
| of custody to the information.
|
| How are "people" _actually_ supposed to know there 's "a
| verifiable chain of custody to the information"?
|
| I think this case is instructive to the workability of
| that idea: https://en.wikipedia.org/wiki/Killian_document
| s_controversy. A major news organization was fooled by a
| forged document _that was later identified as such by
| amateurs_. How is any organization supposed to have "a
| verifiable chain of custody to the information" for
| leaked information? That's the avenue for a lot of
| important information, and without it you'll just have a
| lot more reporting on press releases.
| BobaFloutist wrote:
| Something something block chain something something AI
| something something tokens?
| throwup238 wrote:
| Investors will quickly learn to identify deepfakes if it
| becomes a regular thing. The damage will be everyone else
| on the ground:
| https://news.ycombinator.com/item?id=38157593
| throwup238 wrote:
| _> I suspect in the upcoming election, deepfaking the
| candidates doing something out-of-character would have a
| similar surprising effect._
|
| One frontrunner is about to be convicted and his corporate
| empire dissolved while the other frontrunner is facing an
| impeachment inquiry and his son is about to experience the
| full brunt of the Capitol Hill muckraking process.
|
| Deepfakes aren't even going to register in this election
| (no pun intended).
| specialist wrote:
| Down ballot races are more vulnerable. Especially since
| we no longer have local journalism to help interpret
| events.
| cainxinth wrote:
| > _If the recent history of tech is anything to go by, the
| most popular in-practice use case will be porn_
|
| Recent history? I'm pretty sure as soon as the camera was
| invented, someone took a nude picture with it.
| throwup238 wrote:
| And promptly put it up in the town square to get back at
| someone after a breakup.
| numpad0 wrote:
| This is just my random person take, but personally I'm
| skeptical about generative photorealism - it's just extra
| cognitive load that distracts from payload content, unless some
| audiences needs it as visual aids.
| nonameiguess wrote:
| Is the creation of many unique and realistic looking human
| models often the bottleneck in game development? Personally,
| I'd think rules of play, quality of story, and the
| immersiveness and variety of settings available in the world
| make a game. Give me that and it can be text-based or have
| characters that all look like Pacman for all I care.
| jncfhnb wrote:
| It is not.
|
| However the adaptability of character creators is still a
| hard problem.
|
| Like, I'm not particularly concerned with character
| aesthetics but I still found myself reject every single god
| damned hair style for my male OC in Baldurs Gate 3.
| BobaFloutist wrote:
| Programmers aren't necessarily good at art, and artists
| aren't necessarily good at programming. Good art is
| expensive, or difficult, so if you could get it generated
| (and iterated on) at a very low cost it might make it easier
| to make a game in your office in your spare time without
| having to learn a very different, very difficult discipline
| without much overlap.
| numpad0 wrote:
| To me, it seems people who predicts huge
| impacts/"democratization" from genAI are at best not in the
| market for existing content, or in some other times _hates_
| it. That projects onto predictions.
| jncfhnb wrote:
| Eh. You'll have a very tough time doing better than unreal's
| metahumans.
|
| The most important thing is doing this in a way that works well
| with the lighting and of course being performant. Whenever you
| see something generating avatars, you need to question if it's
| viable in game, because often it's not.
|
| No suit motion capture is already a thing. It's not great, but
| it is a thing. Most games don't actually need that many
| animations.
| jokethrowaway wrote:
| All the 3d models generated by these AI solutions are very
| poor (I think I tried every service and project under the
| sun). So many imperfections it's merely a base or a tool for
| a real 3d artist.
|
| That said metahumans don't look much like the subject imho -
| and scanning with reality scan is a nightmare experience
| jncfhnb wrote:
| Perhaps. But I think mapping scans to meta human type
| models will be the better approach for a long time. If you
| need to create a specific person with high fidelity then
| get an artist. If you just need people then metahumans are
| a great tool.
| Podgajski wrote:
| If kids are depressed from looking at the fakeness of people on
| Instagram, how are they going to feel put up against the
| possibility of these AI created perfected people?
| readyplayernull wrote:
| Same as every time in history when cultures have gone morally
| bankrupt and nobody can be trusted, they'll keep isolating.
| Podgajski wrote:
| How do you become someone people can visibly see as a person
| of trust in a society like this?
|
| I know religion doesn't do it, that's for sure. The only
| thing I can think of is some kind of authenticity.
| mortb wrote:
| New innovations - gives you PTSD every day. Computeres and
| technology used to be fun. It hasn't been for years. We're
| building ourselves a horrible future. If it wasn't my main
| income I would have stopped using them and moved into the
| woods long ago. I've seen this comming. It's no wonder that
| birth rates are plummeting world wide. The only help I can
| think of is divine intervention or if someone has a very
| well hidden plan to work it out. For authenticity to work
| it needs to be universal and I'm not sure that is the case.
| Podgajski wrote:
| Yes, same story for me. But I got out of it in 1999. I
| seem to have mentally foreseen the crash coming and it
| portrayed itself as a mood disorder.
|
| I know many of you will disagree with me on this, but I
| also think a large problem is the increase in both
| extremely low frequency, and radio frequency,
| electromagnetic fields.
|
| No one can tell me that the bloody nose I get whenever I
| use laptops that emit high levels of low frequency
| electromagnetic radiation is psychosomatic.
| imtringued wrote:
| The birth rates are plummeting because people are taking
| longer to start their lives. Women are in school until 23
| and tend to change partners at 26. This means there is a
| 9 year window of being marriable for children until 35 at
| which fertility dramatically declines. I'm talking about
| five trips to an IVF clinic or 75% chance of conception
| using donor eggs for a just a single child.
|
| I don't want to see this too negatively though. In
| principle the pool of women who stay fertile longer will
| outproduce women who lose their fertility too early. It
| also means there is genetic selection for longer
| lifespans in general.
| sumtechguy wrote:
| Reminds me of the plot device from Surrogates
| https://www.imdb.com/title/tt0986263/?ref_=nm_flmg_t_63_act
|
| Basically everyone was afraid to go outside and show their true
| nature and would curate from the safety of their home a perfect
| outward appearance.
| skc wrote:
| The "Mandela Effect" is one day going to be a completely
| understandable and common phenomenon
| DrNosferatu wrote:
| Seems we have finally crossed the uncanny valley...
|
| Hope the benefits will outweigh the dangers!
___________________________________________________________________
(page generated 2023-12-15 23:02 UTC)