Scribbler: Controlling Deep Image Synthesis with Sketch and Color

Abstract

SketchSketch + Color Generated results Figure 1. A user can sketch and scribble colors to control deep image synthesis. On the left is an image generated from a hand drawn sketch. On the right several objects have been deleted from the sketch, a vase has been added, and the color of various scene elements has been constrained by sparse color strokes. AbstractRecently, 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.

Multitask learning on monocular water images: Surface reconstruction and image synthesis

“…To avoid this prerequisite, CycleGAN, DiscoGAN, and DualGAN were designed following the cycle consistency for training using unpaired data. These series of methods have been proven effective in various tasks, such as collection style transfer, object transfiguration, season transfer, and generating photographs from sketches . Motivated by them, we learn the two‐way mapping from water images and their corresponding surface geometries, with forward mapping reconstructing the water surfaces and backward mapping synthesizing photorealistic images of waves.…”

“…These series of methods have been proven effective in various tasks, such as collection style transfer, object transfiguration, season transfer, and generating photographs from sketches. 30 Motivated by them, we learn the two-way mapping from water images and their corresponding surface geometries, with forward mapping reconstructing the water surfaces and backward mapping synthesizing photorealistic images of waves. Moreover, we include a subnetwork in our framework to extract and reuse the lighting conditions from existing images.…”

Transform a Simple Sketch to a Chinese Painting by a Multiscale Deep Neural Network

“…Sketch Inversion [13] is a deep neural network for inverting face sketches to synthesize photorealistic face images in the wild. Scribbler [12] is a deep adversarial image synthesis architecture that is conditioned on sketched boundaries and sparse color strokes to generate realistic cars, bedrooms or faces. Pix2pix [30] is a conditional adversarial network (cGAN) [31]; it learns the mapping from an input image to an output image.…”

“…By using both L1 loss and adversarial loss, the result is more realistic and closer to the human sensory vision. Unlike other works that generate images by sketches, they are usually generating single and straightforward scale images such as faces or bedrooms [12,13]. To produce multi-scale Chinese paintings, we propose a multiscale generative model that consists of a full convolution layer [14], and this generative model can create artworks that have not only local detail information, but also the global framework of the painting.…”

Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation

“…Conditional GAN-based image translation [26,45,63] models have shown remarkable success at taking an abstract input, such as an edge map or a semantic segmentation map, and translating it to a real image. Combining this with a user interface allows a user to quickly create images in the target domain.…”