This AI Performs Super Resolution in Less Than a Second
CSIs Enhance image enlarger is now an actual reality thanks to AI neural network image enlarger algorithms

Follow by Email
The paper "A Fully Progressive Approach to Single-Image Super-Resolution" is available here: A-Man's Caustic scene: Corresponding paper with Vlad Miller's spheres scene: Pick up cool perks on our Patreon page: We would like to thank our generous Patreon supporters who make Two Minute Papers possible: 313V, Andrew Melnychuk, Angelos Evripiotis, Brian Gilman, Christian Ahlin, Christoph Jadanowski, Dennis Abts, Emmanuel, Eric Haddad, Eric Martel, Esa Turkulainen, Evan Breznyik, Geronimo Moralez, Kjartan Olason, Lorin Atzberger, Marten Rauschenberg, Michael Albrecht, Michael Jensen, Milan Lajtoš, Morten Punnerud Engelstad, Nader Shakerin, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Thomas Krcmar, Torsten Reil, Zach Boldyga. Two Minute Papers Merch: US: EU/Worldwide: Thumbnail background image credit: Splash screen/thumbnail design: Felícia Fehér - Károly Zsolnai-Fehér's links: Facebook: Twitter: Web:


Ville Pakarinen : I love how he always calls me a "fellow scholar" even though I don't do shit

Krishna Mohan : Ok. Time to stop buying 1000$ phones. Thanks AI. Just don't kill me in the future.

Moby Motion : Unbelievable. Fast computation is crucial for this technology to see mainstream use - especially since lots of people might want to use it on videos and get rid of 480p once and for all

Bob Salita : GitHub:

Catalepsy : Like those tv shows and movies "Enhance that" 🤣

Reavenk : Great results! The intermediary results look like bilateral blur but then it gets really sharp and detailed really fast. There's some bilaterial blurish areas in some of the final iterative results, but you have to really be looking for it.

SABO FX : *N O F U C K I N G W A Y* !!! This is really amazing! Cannot wait for the photoshop filter! Thanx m8!

phreakinpher : ENHANCE!

Menyhért Márton : What happens when you overdo the up-scaling? I'm curious if these algorithms produce distorted or unrealistic images.

CookingAndJava : Finally the police will actually be able to enhance low resolution surveillance camera footage, like in the movies!

Facebotter : Can't wait to see a similar technique used with audio. We'll be able to watch full-fledged movies from the past as if they were filmed today!

21EC : damn....thats beyond crazy ! its like magic. but when do you think we will see this being used in for example google images...?

Jordan Scarrott : When you quote the time it takes to process these images, do these times not depend on the hardware they're running on? Is there an industry standard for this in this field? I don't know what to make of these times. I love the videos by the way. Really quality stuff

Anton Johansson : Did you have any success on images that werent first down sampled? It (quite reasonably) doesn't like JPEG.

21EC : oh wow....this in realtime could be used for an old game like Doom...the game is really pixelated, so it could be pretty cool to play it with higher res' graphics.

Miguel Pereira : Topaz AI Gigapixel is even better than this, it's mind-blowing

Martin Dariush R. Hansen : Like if you watched in 144p

21EC : perhaps this could also be used in video games...I mean in the future when theyll make this work in realtime

Aadit Doshi : Looks like CSI was just way ahead of its time. ENHANCE!

CooleoBrad : Wow. "Zoom. Enhance." might actually be feasible now!

skierpage : I don't think the AI uses related images to supersample, paper says "All presented models are trained with the DIV2K [34] training set, which contains 800 high-resolution images." If that set includes lots of alligator pictures then the results seem unfair 🙂. But what if the neural network recognize the kind of source picture and then supersampled based on related high-res images? Find higher-resolution pictures of fox fur or alligator skin or that particular village and supersample from training based off that.

Squares : I'd like to see the result on a very low quality image coming from the crop of street webcam ! Like in the movies :)

movax20h : Wow. Amazing technique. Almost magic. It puts details in the image that were not there before. The aligator picture ( 2:22 ) is amazing. You can see that the higher resolution picture has amazing detailed textures that were just smooth color with just few pixels and no texture at all. The algorithm learned what the texture should be based on other surranding features. Magic. There are some minor artifacts in one scene, at 1:41 , the landscape photo of a Greek(?) town with sea - the rocks in bottom right corner gets some additional high frequency texture, which doesn't feel natural. It can be also used as a possibly better subsitute for deconvolutional algorithms, to remove bluring, i.e. due to inaccurate focus. Greate video. Would be nice to mention how it actually works. I guess it is a convolutional deep neural network, so 5 second slide with architecture of the network would be useful.

FredIsMyName22 : Discovered your channel five minutes ago and you have a video on this topic I'm interested in... amazing

Nick Fotopoulos : I can't wait to use this on my old photos, videos, and movies!

BESTIRAQIGAMER : Ill be honest this is my favourite channel on YouTube and i always anticipate and wait for new videos

M Siemons : As a physicist let me remark: the upsampling and making up new pixels is very nice, it is NOT super resolution. Resolution of an image is very well defined in terms of the diffraction limit (the largest spatial frequency transmitted by your imaging system) and there are ways to overcome thus limit with super resolution imaging techniques (often in microscopy). AI does not improve this resolution, but should be seen as a smart interpolation of data/pixels.

John Doe : Enhance 224 to 176. Enhance. Stop. Move in. Stop. Pull out, track right, stop. Center and pull back. Stop. Track 45 right. Stop. Center and stop. Enhance 34 to 36. Pan right and pull back. Stop. Enhance 34 to 46. Pull back. Wait a minute. Go right. Stop. Enhance 57-19. Track 45 left. Stop. Enhance 15 to 23. Give me a hard copy right there.

Max Musterman : thx a lot for making all of those wonderful videos and i will watch every video from you. But it feels like you focus a lot on the visual/grafics area of ai. But i think there are a lot more fields in wich ai is used, in wich i am also very interested. love you whatever you focus on. would also love recommendations of other two minute paper-like ressources. Never forget: what an awesome time to be alife!

Lurker1979 : The print industry will love this. Heck as a photographer I will love this option. Instead of having to cram more and more megapixels on to a chip and making more artifacts. Why not do this instead. Upscale a 20 megapixel image to 50 instead. I could even see this being applied to video. How cool would it be to have a old 60s sitcom that was filmed with TV cameras and has no film and upscale it to full HD.

Albert Gérard : I always knew AI would perform mundane tasks quickly... but this takes things to another level

Shrimp : Nice, hopefully we will see a OpenCL version of this. Would HBCC final bring to a use for privat user with a Vega.

Cameron Kiesser : Can someone enhance the Patterson-Gimlin Bigfoot film?

Dariusz Kajtoch : Great presentation as always! Keep up the great work :)

Luck Searcher : Where can we get the sourcecode from and in which language is it written? Amazing work btw, I started studying AI this week partly because your video make me so excited about it! :)

Saunterblugget Hampterfuppinshire : Wait, can you imagine if we can somehow turn a 144p video to a 4k video. What are the possibilities!

Asenstiven Odin Other : kastakan kastakan 1 месяц назад Наконец, мы будем иметь возможность смотреть японское порно! : D

Panthes Rutler : Looking forward to the day of colour UHD WWII footage in 2.5d.

Money-Gucci-Bitches : is there any webpage or windows install package to play around with this `?

Oscar Barda : I watched this video in 144p, and I have to say, I'm not impressed by the results of this algorithm.

Lagraig O'Moof : Up to 8 times? Doesn't JPEG use 8x8 blocks within an image? This means that an 8x downscaled JPEG file ought to be equivalent to an 8x downscaled version of the original raw image, and so JPEGs would be ideal to train a network like this. i.e. Downscale JPEG 8x as raw pixels, upscale to 8x with the network as a raw image, apply JPEG compression to the output and then compare the 8x8 blocks between the original JPEG and the output.

Diego Antonio Rosario Palomino : Progressive ? It may be usable for dynamic textura filtering

Nono Nono : Can't wait for this to be used in video games to speed up rendering times, or speed up streaming since we can't expect streamed content to be uploading 4k images in real-time.

Jack Sparrow : need 12GB GPU to upscale 520x520 picture 2x. So "1 sec" 30fps video, takes 24s -> 1 min takes 24 mins.

Frane Šustić : Amazing stuff, and what is this slower, superior technique called? Just wondering what quality is possible at this point.

Felix Lipski : <3 <3 <3 I've been waiting for this technology

Alternative Universe Cuts : For 25 years we have all made fun of movies where some technerd enhances a crappy CCTV image to a crisp HD image with some clicks on a computer. Ladies & gentlemen, i think it's about time to stop laughing...

timeofsage : >Looked at their github. >System Requirements >Any NVIDIA GPU with ~12GB memory will do.

Anderson Klein : That is really good to see... Also good would be if people stopped compressing everything down 10000x... Storage is cheap people, no need to fit a 3 hour video in a CD or a photo/audio in a diskette.