Scribbler: Controlling Deep Image Synthesis with Sketch and Color

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)(2016)

引用 571|浏览68
暂无评分
摘要
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.
更多
查看译文
关键词
deep image synthesis,deep convolutional networks,deep adversarial image synthesis architecture,sketched boundaries,sparse color strokes,realistic cars,sketch based image synthesis system,sketch constraints,grayscale images,computer graphics rendering pipeline,Scribbler,realistic imagery generation,feed-forward network,user-guided colorization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要