SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis
This addresses the challenge of sketch-to-image synthesis for applications in computer graphics and vision, offering a more realistic and diverse alternative to existing methods that rely on exact edge maps or retrieval.
The paper tackles the problem of synthesizing realistic images from human-drawn sketches by proposing SketchyGAN, a novel GAN approach that generates plausible images across 50 categories, achieving significantly higher Inception Scores compared to state-of-the-art methods.
Synthesizing realistic images from human drawn sketches is a challenging problem in computer graphics and vision. Existing approaches either need exact edge maps, or rely on retrieval of existing photographs. In this work, we propose a novel Generative Adversarial Network (GAN) approach that synthesizes plausible images from 50 categories including motorcycles, horses and couches. We demonstrate a data augmentation technique for sketches which is fully automatic, and we show that the augmented data is helpful to our task. We introduce a new network building block suitable for both the generator and discriminator which improves the information flow by injecting the input image at multiple scales. Compared to state-of-the-art image translation methods, our approach generates more realistic images and achieves significantly higher Inception Scores.