CVPR 2018: Learning to See in the Dark

Share this video on

What's Hot

What's New

Top Grossing

Top of the Chart

Recommend

Elliot Bridgewater : The future's bright... at night.

Victor Nikolov : I want to implement it in my glasses. :D

Alfredo Fernandes : I had an idea close to that after seeing the Nvidia denoiser for raytracing, shame I didn't had the knowledge to do such, but the results look really great!

Milk Surface : This is amazing!

Matthias Edling : Deep learning is the future and the future is now. Absolutly astonishing work, respect!

Dumb Jason : this is so ridiculously WTF. congratulations on this

Benjamin Healy : Can this be applied to images that have already been compressed? It would be wonderful to be able to recover old shots of mine.

BourbonCreams : 2:13 how did it recognise the 'Digestive' writing on the right of the image?! The original image didn't give any clue about the presence of text.

epSos.de : *Wonderful technology !* If you want to, then people would fund you on crowd funding platforms for bringing this to phones. Let's get this implemented into the open camera on Android, and Gimp for image editing, so that we all can enjoy decent night time photography.

Simeon Radivoev : All we need now is temporal coherence

Darth Jahus : Science is so amazing!

Fly-High : I want plugin for Lightroom!

张志亮 : 好厉害

R3ap3rPy : You are awesome!!!!!!

Kram1032 : Gotta say I'm surprised just how well Google's Pixel 2 camera does at the end at 15fps. - There are some artifacts but I'm almost certain those are from video compression which tends to disproportionately affect darker areas which is problematic if "darker" is the entire image.

Jesper Sahner Pedersen : Wonder if and how this approach will work for videos with extra dimension(s) in terms of movement etc. Maybe future "looks bright" ;)

Carl Ryu : Awesome work. No more YUV pipeline with denoising algo work. Good job

Dmitry Vorobyev : Where I can download it for photoshop?

강동옥 : Result from A7sii with normal low light and intended dark camera settings can be recoverable easily. It should be ultra low light to be meaningful. Please show us the camera settings

Закиров Марат : Could the same results be achieved on compressed data like JPEG -> JPEG? Or it strongly depends on RAW data of specific camera at CANNOT generalize at all?

kihoon kim : awesome

Kerozen : Soon to be wiped of the internet and being picked up by some government or they already have a much more advanced program than this

magnusmoty : This is so very amazing! Will there be simple GUI software capable of doing this available to people?

Tcim : next SOTA!

Big John : The end of photography. AI will take over.

Iluhandric : That's not good brother

Prakash Pandy : How to pass the raw image from iphone camera to it?

Rizki Adi Saputra : improve night vision

LongJohn Vllasaliu : This is ridiculous

Noe Miniel : this is amazing!

Mary Shen : Your work is excellent.

Nikhil Manohar : Stunning work!

RS Z : amazing

sdchew : Very impressive!

Andrew B : Very Impressive!

Joe Hrdina : This is amazing

Wan HL : 1.6s handheld is possible. Olympus em1ii has done it.

Daniel Zuñiga : *i take out my imaginary hat*

vishualee : I'm speechless :O

Graham : Great work, I'm amazed.

Max Mescaline : Magic!

Nikita Nikiforov : it's a kind of magic! you're cool, guys

cfrek : This made me go "holy shit"

rubixjohm : Amazing, great work!

Daniel Holt : E N H A N C E

Hartvik Line : Wow, that is freaking amazing!

sir pei : 凤梨酥看上去很好吃的样子

Виталий Столяров : Amazing!

pd : I hope Samsung incorporate it in Galax S10 :D

AJAY singh : great work