1,000,000,000 Parameter Super Resolution AI!

Подписаться 1,6 млн

Просмотров 141 тыс.

50% 1

❤️ Check out Weights & Biases and say hi in their community forum here: wandb.me/paperforum
📝 The paper "GigaGAN: Scaling up GANs for Text-to-Image Synthesis" is available here:
mingukkang.github.io/GigaGAN/
My latest paper on simulations that look almost like reality is available for free here:
rdcu.be/cWPfD
Or this is the orig. Nature Physics link with clickable citations:
www.nature.com/articles/s4156...
🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Aleksandr Mashrabov, Alex Balfanz, Alex Haro, Andrew Melnychuk, Benji Rabhan, Bret Brizzee, Bryan Learn, B Shang, Christian Ahlin, Geronimo Moralez, Gordon Child, Jace O'Brien, Jack Lukic, John Le, Kenneth Davis, Klaus Busse, Kyle Davis, Lukas Biewald, Martin, Matthew Valle, Michael Albrecht, Michael Tedder, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Rajarshi Nigam, Ramsey Elbasheer, Richard Sundvall, Steef, Taras Bobrovytsky, Ted Johnson, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi.
If you wish to appear here or pick up other perks, click here: / twominutepapers
Thumbnail background design: Felícia Zsolnai-Fehér - felicia.hu
Károly Zsolnai-Fehér's links:
Twitter: / twominutepapers
Web: cg.tuwien.ac.at/~zsolnai/

Наука

Опубликовано:

12 июл 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 414

@sebaccimaster 10 месяцев назад

Upscaling keeps on blowing my mind. Perhaps more than img generation

@rollmell 10 месяцев назад

well wasnt this one technically a mix of image generation and upscaling

@sgttomas 10 месяцев назад

Enhance…. Enhance…. Enhance…. Enhance….. I can see the suspect in the reflection of her eyes. And we all laughed at that!!! 😮

@guepardiez 10 месяцев назад

@@sgttomas We still do. If you can see the suspect in her eyes, it will be a made-up one.

@eyeles 10 месяцев назад

Remember when they said CSI is completely fake because they zoomed in cameras and improved picture quality😂

@PopGoesTheWorld2023 10 месяцев назад

It certainly is more useful working professionally with graphics and layout. Also extend an image with generative fill in the current Photoshop beta has proven to be amazing and extremely helpful in daily work.

@fynnjackson2298 10 месяцев назад

Would love to see an image downscaled in Photoshop, then upscaled, then have the original and the upscaled version compared at different downscaling levels to see where it gets it correct and where it starts to fall apart so to speak. What a time to be alive!

@austinpalis4931 10 месяцев назад

So now we wont only have over-compressed images, but also under-compressed images? De-compressed? over-decompressed? The future is weird man

@sc0rpi0n0 10 месяцев назад

it won't work that way, as the details are 100% daydreamed or generated.

@Yasha_U 10 месяцев назад

@@sc0rpi0n0 thats the point, as a reminder to see what might have been missed in the details a control variable, so to speak?

@spawn142001 10 месяцев назад

The point is to see how good the second image comes out and how it compares and contrasts with the original.

@tuseroni6085 10 месяцев назад

could be a good thing to remind lawyers that this technique is NOT "zoom and enhance" so they don't go entering AI daydreamed details into evidence.

@philip_hofmann 10 месяцев назад

We talked about GigaGAN in the upscaling community in march. Their results look amazing, but since there is no code/models for us to validate their claims on our own input images, we remain sceptical. In contrast DiffBIR (which just released recently), or StableSR, or ResShift, DAT, SRFormer, HAT etc, we can all run them or train models for them ourselves)

@darkandblue4118 10 месяцев назад

Thanks for telling about all the cool projects

@theneonbop 10 месяцев назад

Isn't the code available now? Edit: I guess the code is available but not the model.

@Macatho 10 месяцев назад

Thank you, was looking for this answer as I am currently trying to find a good upscaler. I can do a decent amount of upscaling in automatic 1111 but I run out of memory quite quickly and I need to get to around 10000x10000 in pixels for a decent DPI for actually printing these generated images. As you seem knowledgable, are there any free-to-use models that I could apply? I could even pay a small sum, just not hundreds of dollars per image.

@AgrippaTheMighty 10 месяцев назад

I was just wondering, how about video upscaling?

@Macatho 10 месяцев назад

@@AgrippaTheMighty That's a bit more problematic :) There is research into video and I guess in 2 years this problem will be solved and also Stable Diffusion will be able to generate video. Video is just different in so many ways, if you take a still from a movie, even in 4k, it's horrible quality compared to a photograph in the same resolution. You could of course try to upscale video yourself, just splice the video into images then upscale each image with a low denoising strength. I'm atm upcaling a 1500x2000 image to 15000x20000, it takes around 30 minutes on a 3090rtx 😭😅. What it does is basically breaking the picture down into sub pictures, because the picture as it is does not fit into the video memory, then it upscales each sub picture, stitches them together, then it does a band pass on the stitches and goes through them using a gradient of denoising strengths (that last one was me guessing, but that's what I would have done).

@DeSlagen8 10 месяцев назад

Since I've started watching you, I feel like I forgot how much AI has developed over 3 years, you have to look back to see how insane progress is

@Lucas-po6mn 10 месяцев назад

remember when DallE 1 was impressive, its not even an afterthought now

@itsjustme4026 10 месяцев назад

Gta sa as a kid vs Rdr2 as an adult

@getsideways7257 10 месяцев назад

Still too early to call it "AI"... Just call it NN or ANN

@Lucas-po6mn 10 месяцев назад

@@getsideways7257 no, AI means any bot, hardcoded or with machine learning, what you are referring to is AGI

@M4rt1nX 10 месяцев назад

I'm so happy I found this channel years ago before all that recent AI frenzy. Last week I heard someone say that AI is new and I just though that I've been holding to my pappers for years now.

@ZOMBIEHEADSHOTKILLER 10 месяцев назад

You should do a few videos showing where to get, and how to use, some of these different AIs you show. i know its not your normal thing, but it would be very helpful, and there probably isnt a channel that could do it better.

@nicberry4893 10 месяцев назад

Started watching you junior year of high school. Now I am a senior in college studying cognitive science and AI. Your channel contributed to that decision!

@zRedPlays 10 месяцев назад

I fell off my chair when I saw what this upscaler could do, from the dog to the humans, all those tiny hairs... It brings out so much detail it's hard to believe it's real. Mindblowing

@Cola-42 10 месяцев назад

Okay man, but are you hurt in any way? Do I need to call the ambulance?

@Slav4o911 10 месяцев назад

Yes but the problem is they keep the model for themselves, which means it might not be that impressive in the real world. Stable Diffusion and Topaz Gigapixel are also impressive, it's like you're seeing AI upscaling for the first time.

@zRedPlays 10 месяцев назад

@@Slav4o911 I've already seen upscaling, it's just that this model's quality especially with hair is outstanding. And yeah I'm aware they keep it for themselves, but that pretty much applies to any revolutionary/cutting edge technology

@zRedPlays 10 месяцев назад

@@Cola-42 Nah dude my mind being blown counteracted my fall and I'm now on top of my chair

@Slav4o911 10 месяцев назад

@@zRedPlays Both SD and Topaz can recreate hair. That's why I'm not impressed, unless I see the model for myself or other people not connected to the company test it. Also they've probably hand picked the results.

@cosmicrdt 10 месяцев назад

Are there any public models available to use it yet? I'd love to give it a try.

@psiga 10 месяцев назад

Between simulon featured in Matt Wolfe's most recent video, and GigaGAN here, it feels like a reminder that _yes, the singularity is still on schedule._

@Timotheeee1 10 месяцев назад

would have been nice if they had released the model

@lbgstzockt8493 10 месяцев назад

reminds me of ""Open""AI

@descai10 10 месяцев назад

@@terpy663 people run up to 30b parameter LLMs on their own pcs all the time

@deadman1999 10 месяцев назад

What is Block N Load's prodigy doing here ??

@harrytsang1501 10 месяцев назад

Especially because 1b parameter can fit on most consumer grade GPU nowadays

@bparlan 10 месяцев назад

@@harrytsang1501 we do run 30b parameter LLMs on our own pcs mate. Models are just 30-60gb tenor files. Just 1 GPU can be a huge step into ML!

@signupisannoying 9 месяцев назад

Wow, super cool. We can use this to make decades old photo look clearer.

@piershanson1784 10 месяцев назад

I'm glad to see adversarial networks getting some more love!

@Chris.Davies 10 месяцев назад

0:53 - It almost got the Porsche 356 shape right - but not quite. I am very familiar with it. I give it 7/10 - and eagerly await being able to award 11/10!

@lewisbamford337 10 месяцев назад

Your the only RU-vidr I have notifications on for 😅I just love watching your videos 😊

@Cropinky 10 месяцев назад

the results are really cool, but it has to be mentioned that these are not being upscaled unconditionally, they are being conditioned by a prompt (CLIP) and that's what makes the upscaling so good, also some other cool techniques used in the paper.

@playbyan1453 10 месяцев назад

Upsampling and signal processing goes this far, people who did this paper need more recognition.

@getsideways7257 10 месяцев назад

There is a huge difference between figuring out the fine details and "artistically visualizing" them. The latter can be fun and all, but only the former is useful for serious work.

@zetathix 10 месяцев назад

I just choked my coffee when I saw that enhanced elephant image. That is a really good image to prove the quality.

@Fanny-Fanny 10 месяцев назад

Wow! How long before we can tell an AI 'i want to watch a movie that is The Empire Strikes Back, but done in a Film Noir style, with Ice Cube as Han Solo and where the movie is from the perspective of The Empire being the good guys. Blend with jokes and characters from The Office, and make it 8 x 5 minute long animated cartoons in the style of The Power Puff girls. But add a twist at 3 points in the movie, based on Pulp Fiction and Snow White' and it produces a quality product that is super enjoyable? I think 14 years 3 months and 17 days (approx). That is a time to be alive, I tell you what!

@the_real_glabnurb 10 месяцев назад

I think you should ask ChatGPT that question. After all, who knows better than an AI, what an AI will be capable of?

@Fanny-Fanny 10 месяцев назад

@@the_real_glabnurb good idea! It said 'can eat more'... not even sure what that means?

@Joshua-ew6ks 10 месяцев назад

The zoom and enhance that CSI Shows has used is now real.

@alpuhagame 10 месяцев назад

Pretty much they had this technology 20 years ago, but only now it has surfaced 👌

@Neonalig 10 месяцев назад

Looks like we're progressively getting closer to that CSI Zoom and Enhance effect, but in reality. This theoretically opens up so much in the field of data compression. Whilst not perfectly lossless, you could store images in a literal 1/10th or even 1/100th the fraction of storage, and get a near equivalent output with only minor visual degradation.

@joelface 10 месяцев назад

Interesting! I think the issue is that while the results will look crisp and (probably) realistic, they'll be different each time. So pictures of your friends might not even look like your friends the next time you open the picture. That said, perhaps if you were to store the original image still in fairly high quality it could work. For example, have it upgrade the final difference between say a 2k and an 8k image -- the finer details might not be something you'd notice anyway, but would save a lot of space.

@cthudo 10 месяцев назад

Of course the problem with using this in a CSI context is that these "enhanced" details are completely made up. I can't wait until this actually gets used in court one day and neither judge nor jury have the knowledge to call out the images thus enhanced by law enforcement as what they are: fabrications. I can even see an expert witness arguing "we are using a superhuman AI to reconstruct what the most likely details of this image look like, so it should absolutely be admissable as evidence!"

@noisywan 10 месяцев назад

2:11 I remember laughing at the scenes in movies where the nerd CIA officer enhances the face of a criminal captured from a 320x200 CCTV with the help of hitting ENTER on keyboard:) I used to play games like The Alley Cat on 80x86 IBM Ps/2 machines with CGA video card. What a time to be alive!

@VincentKun 10 месяцев назад

I followed lesson the last semester and my professor pointed out how difficult it is to have disentangled representation, so very Happy to see this results

@cyancoyote7366 10 месяцев назад

Did he ever give a reason as to why? I am genuinely interested. Is it just because there are so many less ways to have separate, narrowly defined representations than a jumbled mess of undefined "black box" representations that don't make intuitive sense for human brains? So is it just like... restricting the neural network to a "human-readable" domain, in a sense?

@Shurgath 10 месяцев назад

Looking forward to your take on the 3D Gaussian Splatting paper! There is also a new paper that just came out, which extends it to dynamic scenes. Seems to work pretty well there as well.

@ivragi 10 месяцев назад

Yeah, but it's GAN. It works in a specific pretrained patterns (e.g. human portrait, dog, elefant) and you need separate models for every new concept. And it works well with GAN-generated images, everything else is turned to mush when converted to format in which those models can work with.

@galgrunfeld9954 10 месяцев назад

This is an absolute game changer! The amount of applications this can have is just absolutely *huge*!

@Mr.MasterOfTheMonsters 10 месяцев назад

All that was missing was combining Upscallers with AI generation to understand what is the image about and keep them as accurate as possible. And it's finally here! I'm guessing this process would cause problems for more complex images or things that are hard to identify, like a gathering or a dense jungle. But who knows.

@spawn142001 10 месяцев назад

AI image generation IS upscaling. It takes an image of 100% noise. And then it denoises it. Removes the noise. Upscalling the software first brings the original image to the target resolution. So it's not individual pixels at a lower res but giant blocks of 100s of pixels at the target higher resolution. Now this is where they are the same. The starting images just appear different. But they essentially do the same thing. The AI de-noises the image in small steps 20-100 times until the target image is found. Go watch a video on how generative AI works. There's a decoder network that translates the query or words into something the second generative network will understand. These two things all though very slightly different under the hood ARE the same thing or the same family of AI. The neural networks are structured in a remarkably similar way all though they might be trained on different data sets. I.e. the encoder networks are trained on images that were taken in high res and manually lowered so that it can compare its output to the original high res and learn from it.

@DajesOfficial 10 месяцев назад

Literally all upscalers work this way. Just with way less parameters and training data

@glr 6 месяцев назад

Need something like this which can handle the continuity of video.

@rebeccawhite5333 10 месяцев назад

Amazing video as always. Would really like to see the pre-pixalated images vs the upscaled ones but I'm assuming those weren't available

@rocco549 10 месяцев назад

Can't wait for it to become available for video restoration. It will create wonders.

@richbynoon 10 месяцев назад

What a time to be alive....another video

@TeamUnpro 10 месяцев назад

so the depixelization we seen in movies is finally real

@Flashbry 10 месяцев назад

That is astounding! What a time to be alive!!!

@alexlohr7366 10 месяцев назад

This is really incredible. However, I can already see people attempting to claim that this could make the classical crime tv "enhance" trope a reality - but the upscaled version does not contain more actual signal, so it only looks like something that could be true, but need not be.

@wojciechfioka5819 10 месяцев назад

Woooow!!! I will try it in some projects!🎉

@swanknightscapt113 10 месяцев назад

I've always known GAN will be making a comeback. SD'd better watch its back!

@spawn142001 10 месяцев назад

Just want to mention this because i can tell from the comments some people dont know. Inage Genrative AI and upscaling AI are almost the samw thing. They are remarkably similar under the hood in how they work and how they are structured. Key differences would be training. Generative had to match images to words and is trained on data sets that have pictures with words stating what the picture is or whats in it. Upscalling you take high resolution pictures, reduce the resolution. Give the network the low res ask for the high res. Compare the output to the original high res, train the network from there. It might even go deeper and do object recognition first on the lower res, to more specifically know what it should fill in the missing pixels with to be more realistic. For example upscaling a dog at low res. You dont see individual hairs, but the network sees its a dog and knows it ahould produce fine hairs in the output. Upscaling IS generative but instead of starting with pure noise, and finding the target image, it starts with a low res image thats first put into a higher target res format (not upscaled just taking individual pixels and scaling them into giant pixels) maybe it even noises this image up a bit before starting. But where they are both the same is they both take the original image, be it pure noise for generation or the lowscale image for upscale. It iteratively removes a little bit of noise in small steps doing 20-100 or more iterarions depending on the structure of that AI until your output image is found. Remove too much noise in one step and your quality goes down significantly. Its alot more nuanced than this, alot of them do things inbetween each step that are difficult to explain here. So that say query "dog with wings" doesnt produce a dog with a tiny wing on its nose and a large wing not attatched in the corner of the screen. It kinda of in somesense fact checks to the query and makes the image more relevant but this has to do with modifying the noise image on each iterative step through a seperate process. Its best to find videos that actually explain the behind the scenes of both upscaling and image generation. These are REALLY good. And its crazy hearing how it actually does it. Theres also different types of image generation. I believe i described a difusion based system. But might have the names mixed up

@cyber1714 10 месяцев назад

WHAT A TIME TO BE ALIVE!!!

@MylonasFilms 10 месяцев назад

So cool. Thanks

@oren000 10 месяцев назад

Looks like the CSI "Enhance... enhance... enhance... " technology is here with us now.

@kenshi21 10 месяцев назад

Everytime mind blowing papers.

@mattmarket5642 10 месяцев назад

The comparison to Stable Diffusion seems WAY off... they must be using the original SD 1.5 from a year ago instead of some of the incredible community-made finetunes or the new SDXL. I'm sure this GAN has it's use cases but I see way more mutilated images compared to SD.

@sevret313 10 месяцев назад

Yes, this is the problem with researchers doing their own benchmark as they're always incentivised to make their competition underperform.

@mattmarket5642 10 месяцев назад

@@sevret313 So very very true. Too bad Károly doesn't call them out when they do such blatant mischaracterization. I've come to realize this channel needs to be taken with a massive grain of salt over the last year, as I've gotten more into the weeds of AI projects.

@DajesOfficial 10 месяцев назад

This paper is 5 months old, so no SD XL back then

@blackcatdevel0per 10 месяцев назад

Wow! Just amazing =)

@jerchongkong5387 10 месяцев назад

This would be very useful on video, there are movies like the star wars prequels that were shot at 1080p, upscaling them to 8K would be easy with this.

@solenoidnull9542 10 месяцев назад

Once this tech is perfected the input resolution almost won't matter to the layman anymore, now someone chooses their output resolution and its viola. Those fine hairs from nothing in the sample show that even 420p video would be crisp 4k with full detail, giving a full experience either way though not technically accurate to the 4k original if it existed.

@AriaAlessandra 10 месяцев назад

I Cant wait for this to be publicly available!!!

@alexmattheis 10 месяцев назад

Absolutly Amazing. 😄

@mocmocmoc13 10 месяцев назад

Holy moist papers! Those super res upscale blows everything we currently have outta the water.

@Dimencia 10 месяцев назад

During one demo, you showed an image being upscaled, then zooming in on some subsection and upscaling that too... what a great example of the power and usefulness of upscaling. If the upscaling is good enough, you could give it a map to have it draw the world I'm still just waiting for some ridiculous new compression ratios using similar techniques, though

@joelface 10 месяцев назад

The issue being that it is fabricating the results, not upscaling to actual truth.

@Shunarjuna 10 месяцев назад

I can’t wait for all these things to come standard with new desktop and laptop computers.

@delpinsky 10 месяцев назад

Out of this world! 🤩

@perplexedon9834 10 месяцев назад

Whats really cool is that this could make video and image compression absurdly good. If you have a fast, local program that can upscale images in ways that are fully plausible to humans, then you only need to store a low res version. Its like how traditional compression can utilise redundancies in an image (like large blocks of the same colour), AI upscaling dependent compression could utilitse redundancy in human perception (fur looks like fur no matter the specific hair orientations). Imagine a 4k movie being stored in 10s of megabytes.

@n0madfernan257 10 месяцев назад

maybe it can now help viewing the skies better with a modest telescope. wat a time to be a.i. !

@annesortland3947 10 месяцев назад

this new Technic is incredible

@ulamss5 10 месяцев назад

Finally a GAN breakthrough!! What a time to be alive!

@DanielLCarrier 10 месяцев назад

I'm hoping for fast enough upscaling that you could have it as a browser addon, and zooming in doesn't make stuff pixelated.

@Blooper1980 10 месяцев назад

NICE!

@Exilum 10 месяцев назад

Now I need to see this applied in stable diffusion. SD tooling is already insane, but I can't imagine how far you could go, especially with things like comfyUI.

@michaelleue7594 10 месяцев назад

Matching up GANs with generative AI is challenging because of how GANs are trained for very, very specific kinds of images. I guess what you could do is have a large list of GANs in A1111 or whatever and then manually select an appropriate GAN for the kind of image you've generated, but unless you're limiting yourself to pretty limited sets of subject matter, you're going to fill up your whole hard drive with GANs pretty quick. Not to mention someone actually has to make the GAN models in the first place, which is far from trivial. These are not simple or small, like Loras.

@Exilum 10 месяцев назад

@@michaelleue7594 People using comfyui already built an habit of using different models for different tasks at each step of their composition, so it wouldn't be that far fetched doing the same with a GAN model. The super-resolution ability would certainly be fit for this workflow.

@michaelleue7594 10 месяцев назад

@@Exilum That's fine, if you're looking for super resolution on a portrait, or for a cat or dog, but you're gonna have a rough time if your composition is even slightly more complex than that. And frankly, there are easier ways to get great resolution on extremely simple compositions already, without resorting to giant, hyper-specific models.

@Exilum 10 месяцев назад

@@michaelleue7594 I mean sure, I won't fight you on this. I do like bringing my guns to a sword fight though, so my hopes and dreams are still there.

@Exilum 10 месяцев назад

@@michaelleue7594 (to clarify, comfyui allows you to work on sections of an image easily, so you can do 100x superresolution per-subject, then bind the seams using another model)

@IN_MY_SHOES_4K 10 месяцев назад

Amazing😊

@grzesiektg 10 месяцев назад

now I want to try it!

@zhin4362 10 месяцев назад

"Zoom! Enhance!"

@EDToasty 10 месяцев назад

seeing Geoffrey Hinton's pixelated face staring in to my soul was not what i needed tonight

@steffenaltmeier6602 10 месяцев назад

somehow the CSI "zoom in on the reflection" meme is becoming reality!

@AlphaVisionPro 10 месяцев назад

I'm testing GigaGan and it works very well.

@magneticflux- 10 месяцев назад

2:07 More like _horse_ input lmao

@AllisterVinris 10 месяцев назад

Mind blowing. Are you going to talk about DLSS3.5 and ray reconstruction or is it not crazy enough ? Because I think I understand how it works, but I wouldn't be against a more precise explanation

@andrewbrock8920 10 месяцев назад

See and click as usual…bravo!

@drkpaladin777 10 месяцев назад

The zoom and enhance feature from all those CSI shows finally works in real life!

@fitybux4664 10 месяцев назад

ENHANCE! ENHANCE! 😎

@sighko05 10 месяцев назад

Detective: “Enhance… enhance… ENHANCE!! Would you look at that; I think we’ve got our guy. Send out an APB for a suspect with really strange hands.”

@tartarosnemesis6227 10 месяцев назад

"Zoom in. More! Now enhance resolution..." A common movie quote now reality.

@elliotmarks06 10 месяцев назад

Can't wait for the code to be released!

@NeilMoore 10 месяцев назад

When you're long gone, an ai will be continuing your work on youtube and it will say "what a time to be dead!" instead of "alive"

@GameNOWRoom 10 месяцев назад

Crazy stuff

@RealitySlipTV 10 месяцев назад

what a time to be alive!

@dr0g_Oakblood 10 месяцев назад

Seems like we're closer and closer to the "zoom and enhance" cliche becoming actually semi-real lmao.

@smilefaxxe2557 10 месяцев назад

CRAZY ❤🔥🔥🔥

@Fx_Explains 10 месяцев назад

i can't wait these to be implemented in VR headsets.

@alejmc 10 месяцев назад

What a marvel of technology. Would it be possible to have a video of how/where to access these tools? Ideally as user friendly as possible first… for example DrawThings works even on iPads but it’s SDXL only to my knowledge and not GAN? (myself I don’t even know the difference yet). Thanks for these videos (and the free Raytracing courses, started watching those and they are a blast!)

@spiritpower3047 10 месяцев назад

Wooow so cool !! 😍 I love it ! How to use this great upsacler please ?

@QuentinKim428 10 месяцев назад

What a time to be alive!!!!!!!!!!!!!

@badpuppy3 10 месяцев назад

I used to watch your videos with excitement. Now I watch them with dread.

@fitybux4664 10 месяцев назад

Could you do a really good infinite zoom with these upscaling techniques? ENHANCE! ENHANCE! 😀

@glenneric1 10 месяцев назад

it would become all hallucination very quickly

@Andreas-gh6is 10 месяцев назад

For such a long time computer scientists laughed at Hollywood's "enhance that image" cliche.

@Yaddlezap 10 месяцев назад

Let's put Patterson-Gimlin footage through this

@BreadedRedBeard 10 месяцев назад

Those upscaling camera technologies on spy movies that corridor digital team used to laugh at on their vfx react videos might not be so far off anymore.

@MattCruikshank 10 месяцев назад

At 2:07 there's a mistake. It says "Coarse," but it's actually spelled "Horse." ;)

@AlucardNoir 10 месяцев назад

Somewhere in Hollywood: YES! Enhance is finally a thing and the nerds can't comment any more!

@gordonfrimann246 10 месяцев назад

thats some CSI level shit, zoom in on that reflection!

@Sekir80 10 месяцев назад

I love the upscaling. I wonder how temporally coherent it is. In other words: can we use this for video upscaling?

@Chaosligend 10 месяцев назад

No. Without any kind of feedback loop of the outputs it's impossible to have any kind of coherence. It's like asking two artists to draw the same image without communicating. The architecture needs significant changes in order to improve temporal coherence. Usually that also means significantly slowing down the model.

@Sekir80 10 месяцев назад

@@Chaosligend Dumb question: how do you know there's no feedback?

@Chaosligend 10 месяцев назад

@@Sekir80 I have a degree in AI and happen to specialize in Computer Vision so I'm familiar with the kind of architecture that the paper is using and what kind of architecture is needed in order to make temporal cohesion. The problem is that at this moment the computers are not nearly strong enough to allow for temporal cohesion with a naive approach. There are some attempts being made to use a very advanced approach to solve this issue but it needs at least a year or two to produce any decent results.

@Sekir80 10 месяцев назад

@@Chaosligend Thank you! I'm not in the field, an expert's opinion is truly appreciated.

@Sekir80 10 месяцев назад

@@acmhfmggru Thanks to you as well! I was asking that, because without understanding the paper (which I didn't read, at all) I can't be certain there's no feedback. But you both telling me that implies the nature of this kind of AI thing isn't meant to do it on itself. And of course, if it would have a temporal coherence part, they would be boasting about it. I think.

@SandMan_86 10 месяцев назад

That's precisely the "enhance" function in star trek...stranger than fiction

@aadmi 10 месяцев назад

Fun fact Raster images can be viewed as vectors with fast upscaling, downscaling

@SylooxD 10 месяцев назад

3:27 Enhance!

@jonorgames6596 10 месяцев назад

Like the police series: "Enhance!" :)

@DanielWhitmer 10 месяцев назад

as good as it is, square pupil and iris on the lady with the necklace was horrifying

@TheSmurfboard 10 месяцев назад

at least she didnt have a third arm

@PushyPawn 10 месяцев назад

What it's like to trip on acid: 1:08

@zdenek7220 10 месяцев назад

...enhance 34 to 36, pan right and pull back, stop, enhance 34 to 47... once there, Im hooked.

@eSKAone- 10 месяцев назад

So sick 🌌💟

@Stalemoldymeme 10 месяцев назад

Enhance. Enhance! ENHANCE!!

@adrianm7203 10 месяцев назад

If you zoom into the upscaled image and then upscale it again could you do an infinite zoom? I wonder what kind of artifacts the upscaler would create.

@michaelleue7594 10 месяцев назад

You could, but it would do a bad job for anything but fractal-style images. It wouldn't know how to just up the resolution. Let's say your GAN is trained on human faces like this one is, then when you zoom in it would try to make the zoomed in portion look like a human face inside of the larger human face. That would end up looking monstrous or stupid for most applications.

@perfectionbox 10 месяцев назад

Read "Blind Lake"

@jejoisland9182 10 месяцев назад

So you are telling me all those crime shows with their fancy enhancement programs were right all along xD

@henryogan2017 10 месяцев назад

Not gonna lie... This is probably the most legitimately exciting research I've seen in a while. This could very well be a first step towards ideal AI art creation, in my opinion