The code is licensed [1] under the "Apple MIT" license [2], which is considered open-source. The weights are under a different, more restrictive license. This is mentioned at the bottom of the README.
This bugs the hell out of me, somehow these companies argue that training on all sort of content without is fine because reasons and then have the audacity to attach a new proprietary licence to it.
It effectively prevents the community from using Apple's solution, but gives the Chinese everything they need to duplicate the results and push their own version.
I expect a Hunyuan-branded version of this model in six months. Probably with lots of improvements.
I'm all for Chinese model takeover if this is how US tech giants treat AI. You can't horde the flames forever, US hyperscalers.
The DoD ought to be advocating for a strong domestic open source stance to ensure our ecosystem doesn't get washed away. AI czar David Sacks has this view, but I suppose it's been falling on deaf ears when the hyperscalers crowd out the conversation.
Meta’s campaign to corrupt the meaning of Open Source was unfortunately very successful and now most people associate releasing the weights with open source.
Actually it is more like all big corps campaigns that have successfully moved away from anything GPL as much as possible, while pushing for business friendly licenses.
Linux kernel and GCC are probably the only thing left they tolerate, and even then, it is less relevant in the cloud, with containers powered by type 1 hypervisors.
Given that it's under scrutiny for regulatory bypass, it's not a purchase and is being reviewed as circumventing those very rules. Might not even happen.
I know, I'm joking: Trump likes Nvidia, but maybe he'll bump the Chinese tax to 30% to approve this deal? In a way I hope he pulls something like that, to punish Huang for his boot shining manipulations.
It's gratifying. I used to tilt at windmills on HN about this and people would be telling me with absolute condescension how the ship had sailed regarding the definition of Open Source, relegating my own life's work to anachronism.
People slowly waking up to how daft and hypecycle misusing a term was all along has been amazing.
The wildest one is how people say just because you produce open source software you should be happy that multibillion dollar corporations are leeching value from your work while not giving anything back but are in fact making your life harder. That’s the biggest piss on my back and tell me it’s raining bullshit I ever heard and makes me not want to open source a damn thing without feeling like a fool.
The GPL is still the answer. Corporate lawyers still avoid it at all costs. The simple requirement that any derivative works bear the same license has always been the key to sustaining the movement, and the whole push toward permissive licensing has been driven by the companies that want to leech.
I think exactly like this. If I created a tool and it were used for free by billion dollar corporations to enrich themselves, I would consider it a personal loss.
so it wasn't a new campaign, it is at best re-appropriating the term open source in the software community in a way communities outside of software have always been using it, in a way that predates software at all, exists in parallel to the software community, and continues to exist now
In 30 years in tech, I have never once heard anyone use the term "Open Source" to refer to anything other than FOSS.
I have also never once heard anyone use the term FOSS outside of the written form.
So the opposite of what you said, I guess.
You also seem to be saying that the term "open source" existed before software did, so I feel compelled to ask: what do you think "source" stands for in "open source"?
The OSI definition and "open source purity" is designed by big tech to erode any value layer open source companies could use to threaten them.
New movements like "fair source", which is a form of source available + free use + expiring copyright is the ideal license. It's effectively unlimited use for customers and users, but has a baked in "non-compete" preventing low effort third parties from coming in and eating the market of managed services established by the authors.
We need to kill open source purity. Especially if we want to erode the hyperscalers that aren't even giving away the magic parts or valuable parts of their kingdoms.
Open source purity is a socialist dream while we're still living under the Empire. And it prevents the formation of a salient that can punch through. It's a very low suboptima.
I don't see any reason why you would want fair source authors to go "OSI" open other than taking their revenue stream as your own. The license bakes in contingencies in case the authors go out of business to open the license up for community ownership. That's good enough.
If these businesses were OSI open, the businessss become unsustainable and impossible to scale into something formidable that could chip away at entirely closed hyperscalers.
How is it not progress? You have full access to the code, you can use it yourself however you'd like, and the copyrights expire.
They just ask you not to compete with them for a few years.
How is that any way comparable to AWS?
Perfect truly is the enemy of good.
In this case, perfect murders good and locks you in the dungeon of eternal bad so you can think endlessly about perfect. It also stabs any good that comes along while crying about perfect.
There's no reason to believe that weights are copyrightable. The only reason to pay attention to this "license" is because it's enforced by Apple, in that sense they can write whatever they want in it, "this model requires giving ownership of your first born son to Apple", etc. The content is irrelevant.
> The only reason to pay attention to this "license" is because it's enforced by Apple
Yes, but the most important reason to pay attention to ANY license for most people is because it is a signal for under what conditions the licensor is likely to sue you (especially in the US, which does not have a general “loser pays” rule for lawsuits), not because of the actual legality, because a lawsuit is a cost most people don’t want to bear while it is ongoing or cover the unrecoverable costs of once it is done, irrespective of winning and losing, and, on the other hand, few people care about being technically legal with their use of copyright protected material if there is no perceived risk of enforcement.
But even if that wasn’t true, and being sued was of no financial or other costs until the case is finally resolved, and only then if you lose, I wouldn't bet much, in the US, in the court system ultimately applying precedent in the most obvious way instead of twisting things in a way which serves the interest of the particular powerful corporate interests involved here.
> This. Tables of numbers are explicitly not subject to copyright; that’s a copyright 101 fact.
Ok, but there's clearly more nuance there. Otherwise I could claim that any mp3 file I wanted to distribute is just a table of 8-bit integers and therefore not subject to copyright.
I wanted to reply in this direction. Ultimately, literally everything and anything in SW is a sequence of numbers, that anybody could easily put in some kind of table form.
I don’t know where the catch is, but that sentence can not be true in general.
That is simply not true. The details might vary by jurisdiction and the protection might not be under the exact name of “copyright” but there most certainly are comparable legal protections for the contents of databases (“tables of numbers”). See for example: https://europa.eu/youreurope/business/running-business/intel...
Disney would like you have a word with you. Why would their pile of numbers that represent Avatar3.m4a be any more subject to copyright than Apple_2D_3D.bin. Or GPT52.mlx or Opus45.gguf?
It's probably just Apple layers avoiding getting involved in any copyright lawsuit over the copyrightability of weights, by avoiding licensing it except under what's clearly fair use anyway, making copyrightability moot.
Yes this seems more about protecting them from a lawsuit. I don’t think they actually give a shit about the weights or they wouldn’t release them at all. I suspect they just know they’re training dataset isn’t perfectly “clean” and don’t want to accept any more liability than they already have.
> There's no reason to believe that weights are copyrightable.
I know this is a long, nuanced, ongoing discussion. I'm very interested in it, but haven't read up on it for years. Could you elaborate a bit on the latest?
I was always in the camp that opined that "weights" are too broad a term for any sensible discussions about conclusions like "are (not) copyrightable". Clearly a weight that's the average of its training data is not copyrightable. But also, surely, weights that are capable of verbatim reproduction of non-trivial copyrightable training data are, because they're just a strange storage medium for the copyright data.
Pretty sure this is a joke, but the actual license is written by lawyers who know what they are doing:
> “Research Purposes” means non-commercial scientific research and
academic development activities, such as experimentation, analysis, testing
conducted by You with the sole intent to advance scientific knowledge and
research. “Research Purposes” does not include any commercial exploitation,
product development or use in any commercial product or service.
It kind of is, though. You use some input material to produce the weights via some process, even if the weights might not become exactly the same every time you reproduce the process; the production of the weights isn't done by working with the weights, but with the training material and the process to convert them into weights. The analogy to source code and the resulting binaries is there.
Training data and the weights produced are not source code, just as access to the resulting binaries are not a requirement for open source.
Open source does not require full working implementations. There's no requirement that a code snippet that I release be fully working and identical to a complete solution.
So we are on agreement that "weights" are not source code. Training data might not also be actual "code", but it is source. After all, the model trained using that data tries to estimate its training data. It is the ground truth for the model.
About the access of binaries or providing working implementations, where did those come from? I don't think this thread was discussing those at all.
Indeed I would be willing to call something an "open source model" if it came without weights, but did come with the training data and with a documented process (preferably executable); and a release with just the training data could be called "open dataset" while the software to run the training would be just plain old open source software.
And, of course, a model with only the model data distributed with an open license is relatively commonly called "open weights", this being pretty self-explanatory term.
If all these AI models were trained on copyrighted materials for which the trainers had no right to, is it wrong to steal their models and use them however we want? Morally I'd say absolutely not, but I"m sure these AI bros would vigorously defend their own IP, even if it was built on stolen IP created by humans.
> If all these AI models were trained on copyrighted materials for which the trainers had no right to, is it wrong to steal their models and use them however we want?
If (which the courts seem to be pretty consistently finding) training models on copyright-protected works generally is fair use, though using models to produce works which would violate copyright if made by other means with reference to the source material is still a copyright violation, then training has no bearing on the legality of copying the models. (Even if it wasn't, then copying and using the models at all would violate the copyright of the original owners of the training material again and be illegal irrespective of the “license” offered by the model trainer.)
Morally? Well, pretty much the same dichotomy applies; if training the model isn't a violation of the source material's creators' rights, then the fact it was trained without permission has no bearing on the morality of using the model without the trainers permission, if it is a violation of the source material's creators' rights, then so is using the model irrespective of the trainer's “license”, as the trainer has no right to permit further use of the material they had no right to create.
The idea that the model is an intrusion on the rights of the creators of the materials used in training and that this makes use of the model more rather than less permissibly, legally or morally, takes some bizarre mental gymnastics.
Making 3D worlds like that is impressive. I used to build some VR worlds (hobby) and content generation is a huge time sink. I wonder if this tech will become accessible for that soon.
This is all going to become super accessible to everyone. And it'll become fast and eventually free.
Everyone will be able to flex their muscles as a creative. Everyone will be able to become an artist (expressing themselves though their unique lens) without putting points into a mechanical skill that is dimensionally orthogonal to idea expression and communication.
This is the "bicycle of the mind" that Steve Jobs talked about 40 some years ago. We've all had keyboards with which to express ourselves and communicate, but soon everyone will be able to visually articulate themselves and their thoughts. It's going to be so uplifting for society.
In fifty years we'll even be able to render our direct thoughts and mold them like clay. Share them directly with one another. Co-think.
Your daily reminder that neural network weights aren't creative work and as such aren't subject to copyright protection in the first place. The “license” is purely cosmetic (or rather, it has an internal purpose: it's being put there by the ML scientists who want to share their work and have to deal with the corporate reluctance to do so).
One of the criteria for being open source is no discrimination against fields of endeavor. This license clearly discriminates against any field of endeavor other than (non-commercial) research.
I don’t agree with this idea that for a model to be open source you have to be able to make a profit off of it. Plenty of open source code licenses doesn’t require that constraint
> The license must not restrict anyone from making use of the program in a specific field of endeavor. For example, it may not restrict the program from being used in a business, [..]
The OSI (a consortium of cloud companies who benefit when you write nonfree software for them) is not actually an authority on what the words "open source" mean, no matter how hard they try to insert themselves into that role.
Models can't be open source anyway, because they don't have source.
While most people follow the OSD criteria, there is nothing that says open source software must follow it. Nor is the OSD the only set of criteria or the only definition.
Open source means the source is available. Anything else is just political.
> Open source means the source is available. Anything else is just political.
We don't have to have this debate again. Folks have tried this rhetorical tack so often there is an entire wikipedia page[1] dedicated to explaining the difference between source available and open source...
This is an opinion article and you should realize that opinions do not make definitions.
"Conversely, Richard Stallman argues the "obvious meaning" of term "open source" is that the source code is public/accessible for inspection, without necessarily any other rights granted"
See, here's another Wikipedia article with another opinion that disagrees, and RMS is obviously an authority.
In my experience the common and accepted definition generally matches with the one the OSI uses, people generally use “shared source” or something to refer to things that don’t fit that
> Open source means the source is available. Anything else is just political.
Where was that defined so? And most of all, given the domain of information technology, who understand open source to cover cases where the source is available ie. only for reviewing?
The purpose of words and terms is so that people can exchange ideas effectively and precisely, without needing to explain the terms every time from the grounds up. Having different groups having divergent definitions on the same words is counterproductive towards that goal. In my view, labeling a release "open source" with very big limitations on how the source is used is just not about marketing, it's miscommunication.
If "open source" and "source available" (and "open weights") mean the same thing, the how come people have come up with the two terms to begin with? The difference is recognized in official contexts as well, i.e. https://web.archive.org/web/20180724032116/https://dodcio.de... (search for "source available"; unfortunately linking directly doesn't seem to work with archive.org pages).
It doesn't seem there is any benefit in using less precise terms when better-defined ones are available.
Anything more than the definition is extra. In this case it's political. That doesn't require a definition.
> The purpose of words and terms is so that people can exchange ideas effectively and precisely, without needing to explain the terms every time from the grounds up.
Do you think the 10 criteria of a non-profit's opinion effectively conveys information without needing to explain the terms from the ground up?
> Having different groups having divergent definitions on the same words is counterproductive
Right, which is why the parent is wrong. It's just an organization's opinion
> If "open source" and "source available" (and "open weights") mean the same thing
They don't mean the same thing and I never claimed they do.
> It doesn't seem there is any benefit in using less precise terms when better-defined ones are available.
Use the more precise terms then. But you can't say the definition of open source is this 10 points of criteria that people disagree about....
Still blows my mind that "binaries available" is called open source in the machine learning sphere. It's like calling Office 2007 open source (as opposed to the current browser versions) because you could run the binaries on a local machine
Apparently licenses no longer have to actually meet all 10 of the criteria listed there to count as open source. OSI says AGPLv3 is open source, for example, even though it fails #10 ("No provision of the license may be predicated on any individual technology or style of interface").
AGPLv3 has provisions that are predicated on remote interaction over computer networks. Put modified AGPLv3 software on a computer that users interact with over RS232 terminals and you don't have to give users the source. Replace those RS232 terminals with X servers that let the users interact with the program over Ethernet and you do have to give those users the source.
That's source-available: you get to see the code and learn from it, but if you're not allowed to use it however you want (with as only common restrictions that you must then credit the creator(s) and also allow others the same freedom on derivative works) then it's not the traditional definition of open source
The output is not automatically metrically scaled (though you can use postprocessing to fix this, it's not part of this model). And you can't really move around much without getting glitches, because it only inferences in one axis. It's also hard capped at 768 pixels + 2 layers.
Besides depth/splatting models have been around for quite a while before this. The main thing this model innovates on is inference speed, but VR porn isn't a use case that really benefits from faster image/video processing, especially since it's still not realtime.
This year has seen a lot of innovation in this space, but it's coming from other image editing and video models.
It's not for moving around, but for turning some image into a stereoscopic one (or 2 side-by-side images if you will). Lots of techniques for this exist, which usually turn an image into depth information using AI and then use any number of approaches to generate/warp 2 offset images from it.
So far the best looking results are still achieved with good old mesh warping and no inpainting at all. This may change that.
Ah, but if we're not talking 6DOF what's new with ml-sharp? We've had good autostereoscopy for a couple of years at least.
> So far the best looking results are still achieved with good old mesh warping and no inpainting at all.
I agree
> This may change that.
Seems not to be the case in my testing. The splats are too fine and sparse to yield an improvement. There are actually better (slower) image -> splat models than ml-sharp (with much higher dynamic range for the covariance) but I still don't use them over meshes for this.
The only improvements ml-sharp seems to add to the SOTA is 1) speed and 2) an interesting 2-focal layer architecture, but these are somewhat tangential steps.
I feel like being in a time loop. Every time a big company releases a model, we debate the definition of open source instead of asking what actually matters. Apple clearly wants the upside of academic credibility without giving away commercial optionality, which isn't unsurprising.
Additionally, we might need better categories. With software, flow is clear (source, build and binary) but with AI/ML, the actual source is an unshippable mix of data, infra and time, and weights can be both product and artifacts.
I'm glad you said it. Incredible tech and the top comment is debating licensing. The demos I've seen of this are incredible and it'll be great taking old photos (that weren't shot with a 'spatial' camera) and experiencing them in VR. I think it sums up the Apple approach to this stuff (actually impacting peoples lives in a positive way) vs the typically techie attitude.
You could use pixi instead, as a much nicer/saner alternative to conda: https://pixi.sh
Though in this particular case, you don't even need conda. You just need python 3.13 and a virtual environment. If you have uv installed, then it's even easier:
git clone https://github.com/apple/ml-sharp.git
cd ml-sharp
uv sync
uv run sharp
Perhaps they lived outside of the kingdom, with an evil Stepmother who moved very slow, struggled with complex dependency collisions, and took up a bunch of unnecessary space? Such an experience could leave one very traumatized towards Conda, even though their real problems are the unresolved issues with their stepmother…
Is this already integrated into the latest iOS? If so it’s not good. It only works on a few images and for the most part the rendering feels fake and somehow incoherent
I’ve been using some time off to explore the space and related projects StereoCrafter and GeometryCrafter are fascinating. Applying this to video adds a temporal consistency angle that makes it way harder and compute intensive, but I’ve “spatialized” some old home videos from the Korean War and it works surprisingly well.
Weird how “hugging face” is a heartwarming little smiley face, while “face hugger” is a terrifying alien xenomorph. Seems like there’s an analogy to be made there…
It seems like it, although the shipped feature doesn’t allow for as much freedom of movement as the demos linked here (which makes sense as a product decision because I assume the farther you stretch it the more likely it is to do something that breaks the illusion)
The “scenes” from that feature are especially good for use as lock screen backgrounds
I assume this is the same spatial scenes feature that was on visionOS prior to OS 26. In my experience that was really incredible. You could take a standard 2D photo of someone and suddenly you were back in the room with them.
It doesn't but it's pretty trivial to do if all you want is a pinholed mesh.
I managed to one-shot it by mixing in the mesh exporter from https://github.com/Tencent-Hunyuan/HunyuanWorld-Mirror but at that point you might as well use HWM, which is slower but much better suited to the level design use case.
Note that the results might not be as good as you expect, because this does not do any angled inpainting -- any deviation from the camera origin and your mesh will be either full of holes or warped (depending on how you handle triangle rejection) unless you layer on other techniques far outside the scope of this model.
And note that although HWM itself does support things like multi-image merging (which ml-sharp does not), in my testing it makes so many mistakes as to be close to useless today.
If you want something different that is designed for levels, check out Marble by World Labs.
I don’t know when Apple turned evil but hard for me to support them further after nearly four decades. Everything they do now is directly opposite of what they stood for in the past.
Apple trying to “open-source” something is pretty relevant. I don’t trust them at all. People constantly go at Microsoft but what Apple has done in the last 15 years is far worse. Their monopolies have had far worse impact than whatever Microsoft ever did with Windows and IE.
The poor industry, self-selecting for high-quality SDKs that macOS won't sign. Wouldn't they be upset if Apple ends up hurting themselves?
As rare as Apple is to admit it, there is this mercurial thing called "competition" that haunts the free market. OpenCL would have had an excellent chance if Apple took it as seriously as Nvidia took CUDA. But they didn't, it was thrown over the fence and expected that everyone else would do the work. While Nvidia was shipping Linux and BSD-native CUDA drivers, Apple was just distributing loose specs and begging the OpenCL working group to stop rewarding their competitor. Not for a lack of funding or motivation, Apple lost because they were butthurt.
OpenCL was DOA the moment Apple stopped treating Nvidia as a proper threat. Everyone else in the industry supported CUDA and was fine with it.
I decidedly disagree with about everything you said regarding Microsoft. The Microsoft monopoly is the most life sucking cancer the corporate world has ever experienced. Compared to that the entire existence of Apple is merely a footnote. Don't mistake your stupid phone for the world.
I sunk my twenties involving the sh*tshow that was Microsoft antitrust. No, Microsoft shipping IE by default is pretty benign compared to what Apple has been doing for far longer than whatever Microsoft ever did. In fact, one can make an argument that Windows was really an open platform for developers based on Today’s standards.
I'm not talking about laughable little stunts like IE. I'm talking about the ongoing cancer that is eating up billions from little companies all the way to big corporations. All of that is ongoing, and they squeeze their prey for everything they have. They are the most disgusting and damaging disease you can imagine.
Once you start using even a small fraction of their tech it instantly metastasises throughout the entire organisation because of lock in and "open standards" that weirdly only work with their own tech. If the MS tech creates a problem the solution is to pour more MS tech onto the festering wound.
You apparently have been so insulated from how actual companies have to deal with tech that you think your little forays using computers are what everything should be measured by. All you have is a developer and hobbyist point of view.
Swift language is open source but the entire ecosystem is as closed as they get. The fact that no one is building anything outside of the ecosystem says everything about Swift and Apple’s intent. The fact that they still won’t support Linux on M chips also says they don’t care.
What would your definition of "instantly" be? I would argue that, compared to taking minutes or hours, taking less than a second is fast enough to be considered "instant" in the colloquial definition. I'll concede that it's not "instant" in the literal definition, but nothing is (because of the principle of locality).
> (...) Now, if I tell someone: "You should come to dinner more punctually; you know it begins at one o'clock exactly"—is there really no question of exactness here? because it is possible to say: "Think of the determination of time in the laboratory or the observatory; there you see what 'exactness' means"? "Inexact" is really a reproach, and "exact" is praise. (...)
Apple is not a serious company if they can't even spin up a simple frontend for their AI innovations. I should not have to install anything to test this.
Literally what this model does- create seemingly 3d scenes from 2d images, in the iOS photos app. It works even better when you take a real spatial image, which uses dual lenses.
This is a free research project on GitHub. I think I'd rather apple focus on making hardware than hoarding GPUs for PR stunts to prove they are a "serious company".
Ah great. Easier for real estate agents to show slow panning around a room, with lame music.
I guess there are other uses?? But this is just more abstracted reality. It will be innacurate just as summaried text is, and future peoples will again have no idea as to reality.
For panning you don't need a 3D view/reconstruction. This also allows translational camera movements, but only for nearby views. Maybe I am overly pedantic here, but for HN I guess thats appropriate :D
HN discussion 11 days ago: https://news.ycombinator.com/item?id=46284658
I love how virtually no GitHub instructions related to AI simply work as written.
Each assumes you already have their developer environment configured to have the tool work, but simply don’t have it compiled yet.
Thanks! Macroexpanded:
SHARP, an approach to photorealistic view synthesis from a single image - https://news.ycombinator.com/item?id=46284658 - Dec 2025 (108 comments)
Examples: https://apple.github.io/ml-sharp/
Paper: https://arxiv.org/abs/2512.10685
imo https://x.com/SadlyItsBradley/status/2001227141300494550 is a better demo than their own project page
https://raw.githubusercontent.com/apple/ml-sharp/refs/heads/...
"Exclusively for research purposes" so not actually open source.
The readme doesn't claim its open source either from what I can tell. Seems to be just a misguided title by the person who submitted it to HN
The only reference seems to be in the acknowledgement, saying that this builds ontop of open source software
The code is licensed [1] under the "Apple MIT" license [2], which is considered open-source. The weights are under a different, more restrictive license. This is mentioned at the bottom of the README.
[1] https://github.com/apple/ml-sharp/blob/main/LICENSE
[2] https://fedoraproject.org/wiki/Licensing/Apple_MIT_License
This bugs the hell out of me, somehow these companies argue that training on all sort of content without is fine because reasons and then have the audacity to attach a new proprietary licence to it.
This is optimally foolish.
It effectively prevents the community from using Apple's solution, but gives the Chinese everything they need to duplicate the results and push their own version.
I expect a Hunyuan-branded version of this model in six months. Probably with lots of improvements.
I'm all for Chinese model takeover if this is how US tech giants treat AI. You can't horde the flames forever, US hyperscalers.
The DoD ought to be advocating for a strong domestic open source stance to ensure our ecosystem doesn't get washed away. AI czar David Sacks has this view, but I suppose it's been falling on deaf ears when the hyperscalers crowd out the conversation.
What DoD has to do with a release of this model?
I guess they're asking for some type of export restrictions.
Link to the actual project license, since it hasn't been referenced yet:
https://github.com/apple/ml-sharp/blob/main/LICENSE
Between this and the model's license, it seems like one is stuck with using this for personal use?
Meta’s campaign to corrupt the meaning of Open Source was unfortunately very successful and now most people associate releasing the weights with open source.
Actually it is more like all big corps campaigns that have successfully moved away from anything GPL as much as possible, while pushing for business friendly licenses.
Linux kernel and GCC are probably the only thing left they tolerate, and even then, it is less relevant in the cloud, with containers powered by type 1 hypervisors.
Releasing weights is fine but you also need to be allowed to... Use the model :P
You’re perfectly free to use it for private use, model output have been deemed public domain
Or you're free to use the output for commercial use if you can get someone else to use the tool to make the (uncopyrighted) output you want.
Isn't that what groq did basically?
Though I'm sure they will shut their shop asap now that Nvidia basically bought them.
Nvidia didn’t buy Groq.
They did (unless you're one of the drafters of the Hart-Scott-Rodino Act, in which case, weirdly, they didn't)
Given that it's under scrutiny for regulatory bypass, it's not a purchase and is being reviewed as circumventing those very rules. Might not even happen.
I know, I'm joking: Trump likes Nvidia, but maybe he'll bump the Chinese tax to 30% to approve this deal? In a way I hope he pulls something like that, to punish Huang for his boot shining manipulations.
#iwantRAM
"basically"
It's deliciously ironic how a campaign to dilute the meaning of free software ended up getting diluted itself.
It's gratifying. I used to tilt at windmills on HN about this and people would be telling me with absolute condescension how the ship had sailed regarding the definition of Open Source, relegating my own life's work to anachronism.
People slowly waking up to how daft and hypecycle misusing a term was all along has been amazing.
We must all choose which hill to die on, and I am glad to have met someone else on that same hill, comrade.
https://www.downloadableisnotopensource.org/
The wildest one is how people say just because you produce open source software you should be happy that multibillion dollar corporations are leeching value from your work while not giving anything back but are in fact making your life harder. That’s the biggest piss on my back and tell me it’s raining bullshit I ever heard and makes me not want to open source a damn thing without feeling like a fool.
The GPL is still the answer. Corporate lawyers still avoid it at all costs. The simple requirement that any derivative works bear the same license has always been the key to sustaining the movement, and the whole push toward permissive licensing has been driven by the companies that want to leech.
At this point the bare minimum for anything new is probably AGPL. Even that needs to be reinforced against hyperscalers and LLMs.
I think exactly like this. If I created a tool and it were used for free by billion dollar corporations to enrich themselves, I would consider it a personal loss.
FOSS = free and open-source software
Open Source =/= free or software, just readable
so it wasn't a new campaign, it is at best re-appropriating the term open source in the software community in a way communities outside of software have always been using it, in a way that predates software at all, exists in parallel to the software community, and continues to exist now
In 30 years in tech, I have never once heard anyone use the term "Open Source" to refer to anything other than FOSS.
I have also never once heard anyone use the term FOSS outside of the written form.
So the opposite of what you said, I guess.
You also seem to be saying that the term "open source" existed before software did, so I feel compelled to ask: what do you think "source" stands for in "open source"?
"Source" can mean any source of information. The term "open source intelligence", referring to public records, goes back to the 60s.
In IT contexts it's used for source code in 99% of situations. Most people have nothing to do with the military or espionage.
The OSI definition and "open source purity" is designed by big tech to erode any value layer open source companies could use to threaten them.
New movements like "fair source", which is a form of source available + free use + expiring copyright is the ideal license. It's effectively unlimited use for customers and users, but has a baked in "non-compete" preventing low effort third parties from coming in and eating the market of managed services established by the authors.
We need to kill open source purity. Especially if we want to erode the hyperscalers that aren't even giving away the magic parts or valuable parts of their kingdoms.
Open source purity is a socialist dream while we're still living under the Empire. And it prevents the formation of a salient that can punch through. It's a very low suboptima.
I don't see any reason why you would want fair source authors to go "OSI" open other than taking their revenue stream as your own. The license bakes in contingencies in case the authors go out of business to open the license up for community ownership. That's good enough.
If these businesses were OSI open, the businessss become unsustainable and impossible to scale into something formidable that could chip away at entirely closed hyperscalers.
Replacing hyperscalers with other hyperscalers born off the back of open source contributors is not exactly progress.
How is it not progress? You have full access to the code, you can use it yourself however you'd like, and the copyrights expire.
They just ask you not to compete with them for a few years.
How is that any way comparable to AWS?
Perfect truly is the enemy of good.
In this case, perfect murders good and locks you in the dungeon of eternal bad so you can think endlessly about perfect. It also stabs any good that comes along while crying about perfect.
And the training data. A truly open source model also includes the training data.
Thank you! Shame all these big corps that do this forever. Meta #1, Apple # 2, psuedo fake journalists # 3
There's no reason to believe that weights are copyrightable. The only reason to pay attention to this "license" is because it's enforced by Apple, in that sense they can write whatever they want in it, "this model requires giving ownership of your first born son to Apple", etc. The content is irrelevant.
> The only reason to pay attention to this "license" is because it's enforced by Apple
Yes, but the most important reason to pay attention to ANY license for most people is because it is a signal for under what conditions the licensor is likely to sue you (especially in the US, which does not have a general “loser pays” rule for lawsuits), not because of the actual legality, because a lawsuit is a cost most people don’t want to bear while it is ongoing or cover the unrecoverable costs of once it is done, irrespective of winning and losing, and, on the other hand, few people care about being technically legal with their use of copyright protected material if there is no perceived risk of enforcement.
But even if that wasn’t true, and being sued was of no financial or other costs until the case is finally resolved, and only then if you lose, I wouldn't bet much, in the US, in the court system ultimately applying precedent in the most obvious way instead of twisting things in a way which serves the interest of the particular powerful corporate interests involved here.
This. Tables of numbers are explicitly not subject to copyright; that’s a copyright 101 fact.
Any of the code that wraps the model or makes it useful is subject to copyright. But the weights themselves are as unrestricted as it gets.
> This. Tables of numbers are explicitly not subject to copyright; that’s a copyright 101 fact.
Ok, but there's clearly more nuance there. Otherwise I could claim that any mp3 file I wanted to distribute is just a table of 8-bit integers and therefore not subject to copyright.
I wanted to reply in this direction. Ultimately, literally everything and anything in SW is a sequence of numbers, that anybody could easily put in some kind of table form.
I don’t know where the catch is, but that sentence can not be true in general.
That is simply not true. The details might vary by jurisdiction and the protection might not be under the exact name of “copyright” but there most certainly are comparable legal protections for the contents of databases (“tables of numbers”). See for example: https://europa.eu/youreurope/business/running-business/intel...
Disney would like you have a word with you. Why would their pile of numbers that represent Avatar3.m4a be any more subject to copyright than Apple_2D_3D.bin. Or GPT52.mlx or Opus45.gguf?
It's probably just Apple layers avoiding getting involved in any copyright lawsuit over the copyrightability of weights, by avoiding licensing it except under what's clearly fair use anyway, making copyrightability moot.
Yes this seems more about protecting them from a lawsuit. I don’t think they actually give a shit about the weights or they wouldn’t release them at all. I suspect they just know they’re training dataset isn’t perfectly “clean” and don’t want to accept any more liability than they already have.
> There's no reason to believe that weights are copyrightable.
I know this is a long, nuanced, ongoing discussion. I'm very interested in it, but haven't read up on it for years. Could you elaborate a bit on the latest?
I was always in the camp that opined that "weights" are too broad a term for any sensible discussions about conclusions like "are (not) copyrightable". Clearly a weight that's the average of its training data is not copyrightable. But also, surely, weights that are capable of verbatim reproduction of non-trivial copyrightable training data are, because they're just a strange storage medium for the copyright data.
What am I missing?
Interesting, the main license doesn't mention the limit, maybe that's why the op got confused
https://github.com/apple/ml-sharp/blob/main/LICENSE
I’m going to research if I can make a profitable product from it. I’ll publish the results of course.
Pretty sure this is a joke, but the actual license is written by lawyers who know what they are doing:
> “Research Purposes” means non-commercial scientific research and academic development activities, such as experimentation, analysis, testing conducted by You with the sole intent to advance scientific knowledge and research. “Research Purposes” does not include any commercial exploitation, product development or use in any commercial product or service.
Should the title be corrected to source-available?
"weights-available" is probably the correct term, since it doesn't look like the training data is available.
Training data is not source code so that's irrelevant
It kind of is, though. You use some input material to produce the weights via some process, even if the weights might not become exactly the same every time you reproduce the process; the production of the weights isn't done by working with the weights, but with the training material and the process to convert them into weights. The analogy to source code and the resulting binaries is there.
Training data and the weights produced are not source code, just as access to the resulting binaries are not a requirement for open source.
Open source does not require full working implementations. There's no requirement that a code snippet that I release be fully working and identical to a complete solution.
So we are on agreement that "weights" are not source code. Training data might not also be actual "code", but it is source. After all, the model trained using that data tries to estimate its training data. It is the ground truth for the model.
About the access of binaries or providing working implementations, where did those come from? I don't think this thread was discussing those at all.
Indeed I would be willing to call something an "open source model" if it came without weights, but did come with the training data and with a documented process (preferably executable); and a release with just the training data could be called "open dataset" while the software to run the training would be just plain old open source software.
And, of course, a model with only the model data distributed with an open license is relatively commonly called "open weights", this being pretty self-explanatory term.
Is there any model that is actually free as in freedom (not necessarily gratis)?
Yes, many models recently have been released under Apache 2.0, both Free and gratis.
I don't think any in this particular space (image-to-3d gaussian representation) are, but then this is the first model I’ve seen in that space at all.
Nice to see some more interesting use of this kind of educational source licensing
If all these AI models were trained on copyrighted materials for which the trainers had no right to, is it wrong to steal their models and use them however we want? Morally I'd say absolutely not, but I"m sure these AI bros would vigorously defend their own IP, even if it was built on stolen IP created by humans.
> If all these AI models were trained on copyrighted materials for which the trainers had no right to, is it wrong to steal their models and use them however we want?
If (which the courts seem to be pretty consistently finding) training models on copyright-protected works generally is fair use, though using models to produce works which would violate copyright if made by other means with reference to the source material is still a copyright violation, then training has no bearing on the legality of copying the models. (Even if it wasn't, then copying and using the models at all would violate the copyright of the original owners of the training material again and be illegal irrespective of the “license” offered by the model trainer.)
Morally? Well, pretty much the same dichotomy applies; if training the model isn't a violation of the source material's creators' rights, then the fact it was trained without permission has no bearing on the morality of using the model without the trainers permission, if it is a violation of the source material's creators' rights, then so is using the model irrespective of the trainer's “license”, as the trainer has no right to permit further use of the material they had no right to create.
The idea that the model is an intrusion on the rights of the creators of the materials used in training and that this makes use of the model more rather than less permissibly, legally or morally, takes some bizarre mental gymnastics.
That sucks.
I'm writing open desktop software that uses WorldLabs splats for consistent location filmmaking, and it's an awesome tool:
https://youtube.com/watch?v=iD999naQq9A
This next year is going to be about controlling a priori what your images and videos will look like before you generate them.
3D splats are going to be incredibly useful for film and graphics design. You can rotate the camera around and get predictable, consistent details.
We need more Gaussian models. I hope the Chinese AI companies start building them.
Making 3D worlds like that is impressive. I used to build some VR worlds (hobby) and content generation is a huge time sink. I wonder if this tech will become accessible for that soon.
This is all going to become super accessible to everyone. And it'll become fast and eventually free.
Everyone will be able to flex their muscles as a creative. Everyone will be able to become an artist (expressing themselves though their unique lens) without putting points into a mechanical skill that is dimensionally orthogonal to idea expression and communication.
This is the "bicycle of the mind" that Steve Jobs talked about 40 some years ago. We've all had keyboards with which to express ourselves and communicate, but soon everyone will be able to visually articulate themselves and their thoughts. It's going to be so uplifting for society.
In fifty years we'll even be able to render our direct thoughts and mold them like clay. Share them directly with one another. Co-think.
Your daily reminder that neural network weights aren't creative work and as such aren't subject to copyright protection in the first place. The “license” is purely cosmetic (or rather, it has an internal purpose: it's being put there by the ML scientists who want to share their work and have to deal with the corporate reluctance to do so).
When AI and open source is used together you can be sure it's not open source.
It’s open source, just not open domain.
One of the criteria for being open source is no discrimination against fields of endeavor. This license clearly discriminates against any field of endeavor other than (non-commercial) research.
https://opensource.org/osd
If it's open source, where are the sources? And how do I make my own from those sources?
I don’t agree with this idea that for a model to be open source you have to be able to make a profit off of it. Plenty of open source code licenses doesn’t require that constraint
https://opensource.org/osd#fields-of-endeavor
> The license must not restrict anyone from making use of the program in a specific field of endeavor. For example, it may not restrict the program from being used in a business, [..]
The OSI (a consortium of cloud companies who benefit when you write nonfree software for them) is not actually an authority on what the words "open source" mean, no matter how hard they try to insert themselves into that role.
Models can't be open source anyway, because they don't have source.
While most people follow the OSD criteria, there is nothing that says open source software must follow it. Nor is the OSD the only set of criteria or the only definition.
Open source means the source is available. Anything else is just political.
> Open source means the source is available. Anything else is just political.
We don't have to have this debate again. Folks have tried this rhetorical tack so often there is an entire wikipedia page[1] dedicated to explaining the difference between source available and open source...
[1]: https://en.wikipedia.org/wiki/Source-available_software
This is an opinion article and you should realize that opinions do not make definitions.
"Conversely, Richard Stallman argues the "obvious meaning" of term "open source" is that the source code is public/accessible for inspection, without necessarily any other rights granted"
See, here's another Wikipedia article with another opinion that disagrees, and RMS is obviously an authority.
https://en.wikipedia.org/wiki/Open_source#%22Open%22_versus_...
All of this is pointless so the common and accepted definition should be preferred. Which does not add extra political criteria for requirements.
In my experience the common and accepted definition generally matches with the one the OSI uses, people generally use “shared source” or something to refer to things that don’t fit that
Something we still often miss, however, is the difference between open source and free software.
What is that difference?
The definitions from the FSF and OSI are very similar, and the lists of approved licenses are mostly the same.
> Open source means the source is available. Anything else is just political.
Where was that defined so? And most of all, given the domain of information technology, who understand open source to cover cases where the source is available ie. only for reviewing?
The purpose of words and terms is so that people can exchange ideas effectively and precisely, without needing to explain the terms every time from the grounds up. Having different groups having divergent definitions on the same words is counterproductive towards that goal. In my view, labeling a release "open source" with very big limitations on how the source is used is just not about marketing, it's miscommunication.
If "open source" and "source available" (and "open weights") mean the same thing, the how come people have come up with the two terms to begin with? The difference is recognized in official contexts as well, i.e. https://web.archive.org/web/20180724032116/https://dodcio.de... (search for "source available"; unfortunately linking directly doesn't seem to work with archive.org pages).
It doesn't seem there is any benefit in using less precise terms when better-defined ones are available.
> Where was that defined so?
Anything more than the definition is extra. In this case it's political. That doesn't require a definition.
> The purpose of words and terms is so that people can exchange ideas effectively and precisely, without needing to explain the terms every time from the grounds up.
Do you think the 10 criteria of a non-profit's opinion effectively conveys information without needing to explain the terms from the ground up?
> Having different groups having divergent definitions on the same words is counterproductive
Right, which is why the parent is wrong. It's just an organization's opinion
> If "open source" and "source available" (and "open weights") mean the same thing
They don't mean the same thing and I never claimed they do.
> It doesn't seem there is any benefit in using less precise terms when better-defined ones are available.
Use the more precise terms then. But you can't say the definition of open source is this 10 points of criteria that people disagree about....
Now you get to graduate into the pedantry of defining the word “source”.
There's no reason for pedantry. Source is pretty well defined.
Which is how we know that AI models don't have any - and therefore can't be open source.
Still blows my mind that "binaries available" is called open source in the machine learning sphere. It's like calling Office 2007 open source (as opposed to the current browser versions) because you could run the binaries on a local machine
Apparently licenses no longer have to actually meet all 10 of the criteria listed there to count as open source. OSI says AGPLv3 is open source, for example, even though it fails #10 ("No provision of the license may be predicated on any individual technology or style of interface").
AGPLv3 has provisions that are predicated on remote interaction over computer networks. Put modified AGPLv3 software on a computer that users interact with over RS232 terminals and you don't have to give users the source. Replace those RS232 terminals with X servers that let the users interact with the program over Ethernet and you do have to give those users the source.
That's pure sophistry, do better. You can start by quoting the part of AGPLv3 that specifically mentions Ethernet.
You also need to explain how a set of terminals connected via RS232 does not constitute a "computer network".
An RS232 connection between serial ports on a computer and terminal has generally never been considered to be a network.
That's source-available: you get to see the code and learn from it, but if you're not allowed to use it however you want (with as only common restrictions that you must then credit the creator(s) and also allow others the same freedom on derivative works) then it's not the traditional definition of open source
And you would be wrong as a simple question of fact.
Do you think the OSD is law or something?
Who said anything about law?
The only popular one I know is CC-NC but that is not open source
This is a dupe. A couple of weeks ago I forked it and got the rendering to work in MPS: https://github.com/rcarmo/ml-sharp
Thanks! This looks nice
Big day for VR pornography!
I'm not kidding. That's going to be >80% of the images/videos synthesized with this.
Unfortunately not as significant as you'd think.
The output is not automatically metrically scaled (though you can use postprocessing to fix this, it's not part of this model). And you can't really move around much without getting glitches, because it only inferences in one axis. It's also hard capped at 768 pixels + 2 layers.
Besides depth/splatting models have been around for quite a while before this. The main thing this model innovates on is inference speed, but VR porn isn't a use case that really benefits from faster image/video processing, especially since it's still not realtime.
This year has seen a lot of innovation in this space, but it's coming from other image editing and video models.
It's not for moving around, but for turning some image into a stereoscopic one (or 2 side-by-side images if you will). Lots of techniques for this exist, which usually turn an image into depth information using AI and then use any number of approaches to generate/warp 2 offset images from it.
So far the best looking results are still achieved with good old mesh warping and no inpainting at all. This may change that.
Ah, but if we're not talking 6DOF what's new with ml-sharp? We've had good autostereoscopy for a couple of years at least.
> So far the best looking results are still achieved with good old mesh warping and no inpainting at all.
I agree
> This may change that.
Seems not to be the case in my testing. The splats are too fine and sparse to yield an improvement. There are actually better (slower) image -> splat models than ml-sharp (with much higher dynamic range for the covariance) but I still don't use them over meshes for this.
The only improvements ml-sharp seems to add to the SOTA is 1) speed and 2) an interesting 2-focal layer architecture, but these are somewhat tangential steps.
Gives the term "Gaussian splat" an entirely different meaning...
Now I know what Gaussian scattering is.
I feel like being in a time loop. Every time a big company releases a model, we debate the definition of open source instead of asking what actually matters. Apple clearly wants the upside of academic credibility without giving away commercial optionality, which isn't unsurprising.
Additionally, we might need better categories. With software, flow is clear (source, build and binary) but with AI/ML, the actual source is an unshippable mix of data, infra and time, and weights can be both product and artifacts.
I'm glad you said it. Incredible tech and the top comment is debating licensing. The demos I've seen of this are incredible and it'll be great taking old photos (that weren't shot with a 'spatial' camera) and experiencing them in VR. I think it sums up the Apple approach to this stuff (actually impacting peoples lives in a positive way) vs the typically techie attitude.
> which isn't unsurprising
There has to be an easier combination of words for conveying the same thing.
I don't think it isn't unsurprising :)
Wait so you are surprised?
I wonder if it helps that a lot of people take more than one picture of the same thing, thus providing them with effectively stereoscopic images.
Also, frames from live photos
Previous discussion: https://news.ycombinator.com/item?id=46284658
I was thinking of testing it, but I have an irrational hatred for Conda.
You could use pixi instead, as a much nicer/saner alternative to conda: https://pixi.sh
Though in this particular case, you don't even need conda. You just need python 3.13 and a virtual environment. If you have uv installed, then it's even easier:
You can simply use a `uv` env instead?
You aren't being irrational.
Perhaps they lived outside of the kingdom, with an evil Stepmother who moved very slow, struggled with complex dependency collisions, and took up a bunch of unnecessary space? Such an experience could leave one very traumatized towards Conda, even though their real problems are the unresolved issues with their stepmother…
Is this already integrated into the latest iOS? If so it’s not good. It only works on a few images and for the most part the rendering feels fake and somehow incoherent
no
I’ve been using some time off to explore the space and related projects StereoCrafter and GeometryCrafter are fascinating. Applying this to video adds a temporal consistency angle that makes it way harder and compute intensive, but I’ve “spatialized” some old home videos from the Korean War and it works surprisingly well.
https://github.com/TencentARC/StereoCrafter https://github.com/TencentARC/GeometryCrafter
I would love to see your examples.
OP probably can’t tell if you're being upvoted on this.
I’d be keen too.
Hugging Face model: https://huggingface.co/apple/Sharp and demo: https://huggingface.co/spaces/ronedgecomb/ml-sharp
Weird how “hugging face” is a heartwarming little smiley face, while “face hugger” is a terrifying alien xenomorph. Seems like there’s an analogy to be made there…
Anyone's aware of something similar for making interactive (or video) tours of apartments from photos?
Is this the same model as the “Spatial Scenes” feature in iOS 26? If so, it’s been wildly impressive.
It seems like it, although the shipped feature doesn’t allow for as much freedom of movement as the demos linked here (which makes sense as a product decision because I assume the farther you stretch it the more likely it is to do something that breaks the illusion)
The “scenes” from that feature are especially good for use as lock screen backgrounds
Ya, I like when it’s automatically done on my featured photo, gives the phone a very 3D look and feel.
I am thinking the same thing, and I do love the effect in iOS26
I assume this is the same spatial scenes feature that was on visionOS prior to OS 26. In my experience that was really incredible. You could take a standard 2D photo of someone and suddenly you were back in the room with them.
Is the model in ONNX format or PyTorch format?
does it make a mesh?
doesn't seem very accurate, no idea of the result with a photo of large scene, that could be useful for level designers
It doesn't but it's pretty trivial to do if all you want is a pinholed mesh.
I managed to one-shot it by mixing in the mesh exporter from https://github.com/Tencent-Hunyuan/HunyuanWorld-Mirror but at that point you might as well use HWM, which is slower but much better suited to the level design use case.
Note that the results might not be as good as you expect, because this does not do any angled inpainting -- any deviation from the camera origin and your mesh will be either full of holes or warped (depending on how you handle triangle rejection) unless you layer on other techniques far outside the scope of this model.
And note that although HWM itself does support things like multi-image merging (which ml-sharp does not), in my testing it makes so many mistakes as to be close to useless today.
If you want something different that is designed for levels, check out Marble by World Labs.
No
Gaussian splats
License arguments aside, pretty cool.
facebook worked on a similar project almost 5 years back
I don’t know when Apple turned evil but hard for me to support them further after nearly four decades. Everything they do now is directly opposite of what they stood for in the past.
Curious what this has to do with the post?
Apple trying to “open-source” something is pretty relevant. I don’t trust them at all. People constantly go at Microsoft but what Apple has done in the last 15 years is far worse. Their monopolies have had far worse impact than whatever Microsoft ever did with Windows and IE.
What would you suggest they have done here?
Yeah Apple was on a good track for a while with things like OpenCL. But completely reversed course :(
Well, the industry rejected OpenCL in favor of proprietary CUDA. Oh well...
The poor industry, self-selecting for high-quality SDKs that macOS won't sign. Wouldn't they be upset if Apple ends up hurting themselves?
As rare as Apple is to admit it, there is this mercurial thing called "competition" that haunts the free market. OpenCL would have had an excellent chance if Apple took it as seriously as Nvidia took CUDA. But they didn't, it was thrown over the fence and expected that everyone else would do the work. While Nvidia was shipping Linux and BSD-native CUDA drivers, Apple was just distributing loose specs and begging the OpenCL working group to stop rewarding their competitor. Not for a lack of funding or motivation, Apple lost because they were butthurt.
OpenCL was DOA the moment Apple stopped treating Nvidia as a proper threat. Everyone else in the industry supported CUDA and was fine with it.
I decidedly disagree with about everything you said regarding Microsoft. The Microsoft monopoly is the most life sucking cancer the corporate world has ever experienced. Compared to that the entire existence of Apple is merely a footnote. Don't mistake your stupid phone for the world.
I sunk my twenties involving the sh*tshow that was Microsoft antitrust. No, Microsoft shipping IE by default is pretty benign compared to what Apple has been doing for far longer than whatever Microsoft ever did. In fact, one can make an argument that Windows was really an open platform for developers based on Today’s standards.
I'm not talking about laughable little stunts like IE. I'm talking about the ongoing cancer that is eating up billions from little companies all the way to big corporations. All of that is ongoing, and they squeeze their prey for everything they have. They are the most disgusting and damaging disease you can imagine.
Once you start using even a small fraction of their tech it instantly metastasises throughout the entire organisation because of lock in and "open standards" that weirdly only work with their own tech. If the MS tech creates a problem the solution is to pour more MS tech onto the festering wound.
You apparently have been so insulated from how actual companies have to deal with tech that you think your little forays using computers are what everything should be measured by. All you have is a developer and hobbyist point of view.
> Apple trying to “open-source” something
You know Apple releases/funds a lot of open source, right?
Projects like WebKit, LLVM/clang, or CUPS (the print drivers for all of Linux)...
Apple has not been nice and open since the 1970s. The only open and nice person in any important role is Wozniak.
Apple absolute Never believed in open source in the past so yes. They are not the same
Where does Swift fit into this? I haven’t followed along but believe it’s open source and a search appears to confirm this?
Swift language is open source but the entire ecosystem is as closed as they get. The fact that no one is building anything outside of the ecosystem says everything about Swift and Apple’s intent. The fact that they still won’t support Linux on M chips also says they don’t care.
Not never. Woz championed some of that in the 1970s. It's before my time, but the Apple II was pretty open as I understand it.
"Sharp Monocular View Synthesis in Less Than a Second"
"Less than a second" is not "instantly".
If you're concerned by that, I have some bad news about instant noodles.
Folgers on line one.
What would your definition of "instantly" be? I would argue that, compared to taking minutes or hours, taking less than a second is fast enough to be considered "instant" in the colloquial definition. I'll concede that it's not "instant" in the literal definition, but nothing is (because of the principle of locality).
Wittgenstein, Philosophical Investigations, §88:
> (...) Now, if I tell someone: "You should come to dinner more punctually; you know it begins at one o'clock exactly"—is there really no question of exactness here? because it is possible to say: "Think of the determination of time in the laboratory or the observatory; there you see what 'exactness' means"? "Inexact" is really a reproach, and "exact" is praise. (...)
would love a multi-image version of this.
Damn. I recall UC Davis was working on this sort of problem for CCTV footage 20 years ago, but this is really freakin' progress now.
Apple is not a serious company if they can't even spin up a simple frontend for their AI innovations. I should not have to install anything to test this.
It's included in the ios photo gallery. I think this is a separate release of the tech underneath.
What user feature does it power?
Literally what this model does- create seemingly 3d scenes from 2d images, in the iOS photos app. It works even better when you take a real spatial image, which uses dual lenses.
This is a free research project on GitHub. I think I'd rather apple focus on making hardware than hoarding GPUs for PR stunts to prove they are a "serious company".
Ah great. Easier for real estate agents to show slow panning around a room, with lame music.
I guess there are other uses?? But this is just more abstracted reality. It will be innacurate just as summaried text is, and future peoples will again have no idea as to reality.
For panning you don't need a 3D view/reconstruction. This also allows translational camera movements, but only for nearby views. Maybe I am overly pedantic here, but for HN I guess thats appropriate :D
For a good slow pan, you don’t need 3d reconstruction but you DO need “Ashokan Farewell”
It will be used for spatial content, for viewing in Apple Vision Pro headset.
In fact you can already turn any photo into spatial content. I’m not sure if it’s using this algorithm or something else.
It’s nice to view holiday photos with spatial view … it feels like you’re there again. Same with looking at photos of deceased friends and family.