Scribbler: Controlling Deep Image Synthesis with Sketch and Color

Authors:
  • PSPatsorn Sangkloy
    Patsorn Sangkloy
  • CFChen Fang
    Chen Fang
  • FYFisher Yu
    Fisher Yu
  • JHJames Hays
    James Hays
Top Cited Papers
Publisher website
Google Scholar
Abstract
Several recent works have used deep convolutional networks to generate realistic imagery. 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 generates more realistic, diverse, and controllable outputs. The architecture is also effective at user-guided colorization of grayscale images.

This publication has 21 references indexed in Scilit: