TextureGAN: Controlling Deep Image Synthesis with Texture Patches
نویسندگان
چکیده
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.
منابع مشابه
Super-resolution Using Constrained Deep Texture Synthesis
Hallucinating high frequency image details in single image superresolution is a challenging task. Traditional super-resolution methods tend to produce oversmoothed output images due to the ambiguity in mapping between low and high resolution patches. We build on recent success in deep learning based texture synthesis and show that this rich feature space can facilitate successful transfer and s...
متن کاملCreating Large Isotropic Textures Using Image Quilting
Image quilting is a texture synthesis technique to create a large texture by wrapping around patches of a small texture in a way that the repetition of small texture is not noticeable. The basic algorithm is to randomly select small patches in a given texture. These patches are then positioned in a large texture to be synthesized and blended across boundaries to remove the appearance of boundar...
متن کاملTexture Transfer Using Affine Transformation Groups and Patch Boundary Matching
An algorithm for performing texture transfer based on an affine transformation model is presented. Image textures are modelled by placing a single patch of texture, a prototype patch, from which the texture is derived using a set of affine transformations. Overlapping target patches covering the entire image are used and a corresponding set of transformations are found to map the prototype patc...
متن کاملPatch-based Texture Synthesis for Image Inpainting
Image inpaiting is an important task in image processing and vision. In this paper, we develop a general method for patch-based image inpainting by synthesizing new textures from existing one. A novel framework is introduced to find several optimal candidate patches and generate a new texture patch in the process. We form it as an optimization problem that identifies the potential patches for s...
متن کاملÖööøøòò Ääööö Á×óøöóôôô Ìüøùöö× Í××òò Áññññ Éùùðøøòò Ëëòòòú ú Øøø Ôôöøññòø Óó Ååøøøññøøø× ² Óñôùøøö Ëëëëòòò Íòòúúö××øý Ó Åå××óùöö ß Ëøº Äóùù× Ëøº Äóùù׸åç ¿½¾½¸íëë ××òòòúúúúñºóöö
Image quilting is a texture synthesis technique to create a large texture by wrapping around patches of a small texture in a way that the repetition of small texture is not noticeable. The basic algorithm is to randomly select small patches in a given texture. These patches are then positioned in a large texture to be synthesized and blended across boundaries to remove the appearance of boundar...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1706.02823 شماره
صفحات -
تاریخ انتشار 2017