Project Scribbler

Patsorn Sangkloy

Georgia Tech

Wenqi Xian

Georgia Tech

Jingwan (Cynthia) Lu

Adobe Research

Chen Fang

Adobe Research

Fisher Yu

Berkeley

Amit Raj

Georgia Tech

Varun Agrawal

Georgia Tech

James Hayes

Georgia Tech

Adobe Max 2017  (#ProjectScribbler  #ProjectsScribbler)

Recently, there have been several promising methods to generate realistic imagery from deep convolutional networks. These methods sidestep the traditional computer graphics rendering pipeline and instead generate imagery at the pixel level by learning from large collections of photos (e.g. faces or bedrooms). However, these methods are of limited utility because it is difficult for a user to control what the network produces. In this paper, we propose a deep adversarial image synthesis architecture that is conditioned on sketched boundaries and sparse color strokes to generate realistic cars, bedrooms, or faces. We demonstrate a sketch based image synthesis system which allows users to ‘scribble’ over the sketch to indicate preferred color for objects. Our network can then generate convincing images that satisfy both the color and the sketch constraints of user. The network is feed-forward which allows users to see the effect of their edits in real time. We compare to recent work on sketch to image synthesis and show that our approach can generate more realistic, more diverse, and more controllable outputs. The architecture is also effective at user-guided colorization of grayscale images.

Sketch colorization

Photo colorization

Interactive control

Scribbler in the news:

9to5Mac “Adobe’s Project Scribbler uses AI to colorize any black and white photo in seconds

Engadget “Adobe’s Scribbler AI automatically colorizes any portrait

DigitalTrends “In sneak preview, Adobe shows off tech for automatically colorizing old photos

SlashGear “Adobe Scribbler AI can create a realistic color image from a sketch

PetaPixel “Adobe Scribbler Can Auto Colorize B&W Photos

DigitalArts “Adobe shows still-in-development tools, including automatically colourising black-and-white photos

PopularScience “Adobe is training AI to be a better photo and video editor than you

Project Publications

Scribbler: Controlling Deep Image Synthesis with Sketch and Color

Sangkloy, P., Lu, J., Fang, C., Yu, F., Hays, J. (Jul. 1, 2017)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2017.

TextureGAN: Controlling Deep Image Synthesis with Texture Patches

Xian, W., Sankloy, P., Agrawal, V., Raj, A., Lu, J., Fang, C., Yu, F., Hays, J. (Jun. 17, 2018)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR Spotlight) , 2018