TextureGAN: Controlling Deep Image Synthesis with Texture Patches
This addresses the need for enhanced user control in image synthesis for creative applications, though it is incremental by adding texture control to existing sketch and color methods.
The paper tackles the problem of controlling deep image synthesis with texture patches, enabling users to place texture patches on sketches to guide output textures, and results show the algorithm generates plausible images faithful to user controls with more realistic outputs than adapted existing methods.
In this paper, we investigate deep image synthesis guided by sketch, color, and texture. Previous image synthesis methods can be controlled by sketch and color strokes but we are the first to examine texture control. We allow a user to place a texture patch on a sketch at arbitrary locations and scales to control the desired output texture. Our generative network learns to synthesize objects consistent with these texture suggestions. To achieve this, we develop a local texture loss in addition to adversarial and content loss to train the generative network. We conduct experiments using sketches generated from real images and textures sampled from a separate texture database and results show that our proposed algorithm is able to generate plausible images that are faithful to user controls. Ablation studies show that our proposed pipeline can generate more realistic images than adapting existing methods directly.