An image compression approach capable of exploiting redundancies in groups of images is introduced. The approach is based on image segmentation, texture analysis and texture synthesis. The proposed algorithm extracts textured regions from an image and merges them with similar texture data from other images, in order to take advantage of textural re-occurrences between the images. The texture ex...

Procedural textures often expose a set of parameters controlling their final appearance. This lets end users tune the final look and feel, typically through a set of sliders. However, it is difficult to predict the changes introduced by a given slider, especially as sliders interact in non–trivial ways. We augment the sliders controlling parameters with visual previews revealing the changes tha...

We present a procedural method for synthesizing large textures from an input texture sample. The basis of our algorithm is the chaos mosaic, a technique for synthesizing textures with an even and visually stochastic distribution of the local features of the input sample. The chaos mosaic is fast. For synthesizing textures of the same size and comparable quality, our algorithm is orders of magni...

Starting from a sample of a given size, texture synthesis algorithms are used to create larger texture images. A good algorithm produces synthesized textures that are pixelwise different but perceptually indistinguishable from the original image. The sample image should be chosen ensuring that it contains a number of pattern repetitions sufficient to produce valuable synthesis results. Since te...

This paper presents an analytical extension of texture synthesis techniques based on the distribution of elementary texture components. Our approach is similar to the bombing, cellular, macrostructured and lapped textures techniques, but provides the user with more control on both the texture analysis and synthesis phases. Therefore, high quality results can be obtained for a large number of st...

This paper introduces a novel approach to texture synthesis based on generative adversarial networks (GAN) (Goodfellow et al., 2014), and call this technique Periodic Spatial GAN (PSGAN). The PSGAN has several novel abilities which surpass the current state of the art in texture synthesis. First, we can learn multiple textures, periodic or non-periodic, from datasets of one or more complex larg...

Despite the tremendous rendering power offered by modern GPUs, real-time and photo-realistic rendering is still often out of reach of traditional polygonal-based rendering. Thanks to the invention of texture mapping, a scene with a moderate number of triangles could be readily and vividly rendered by nowadays popular and inexpensive graphics cards. However, as a desired texture often comes with...

This paper proposes Markovian Generative Adversarial Networks (MGANs), a method for training generative neural networks for efficient texture synthesis. While deep neural network approaches have recently demonstrated remarkable results in terms of synthesis quality, they still come at considerable computational costs (minutes of run-time for low-res images). Our paper addresses this efficiency ...

Skin is noticeably bumpy in character, which is clearly visible in close-up shots in a film or game. Methods that rely on simple texture-mapping of faces lack such high frequency shape detail, which makes them look non-realistic. More specifically, this detail is usually ignored in real-time applications, or is drawn in manually by an artist. In this paper, we present techniques for capturing a...