Browsing by Author "Lutz, Nicolas"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Cyclostationary Gaussian Noise: Theory and Synthesis
    (The Eurographics Association and John Wiley & Sons Ltd., 2021) Lutz, Nicolas; Sauvage, Basile; Dischler, Jean-Michel; Mitra, Niloy and Viola, Ivan
    Stationary Gaussian processes have been used for decades in the context of procedural noises to model and synthesize textures with no spatial organization. In this paper we investigate cyclostationary Gaussian processes, whose statistics are repeated periodically. It enables the modeling of noises having periodic spatial variations, which we call "cyclostationary Gaussian noises". We adapt to the cyclostationary context several stationary noises along with their synthesis algorithms: spot noise, Gabor noise, local random-phase noise, high-performance noise, and phasor noise. We exhibit real-time synthesis of a variety of visual patterns having periodic spatial variations.
  • Thumbnail Image
    Item
    Preserving the Autocovariance of Texture Tilings Using Importance Sampling
    (The Eurographics Association and John Wiley & Sons Ltd., 2023) Lutz, Nicolas; Sauvage, Basile; Dischler, Jean-Michel; Myszkowski, Karol; Niessner, Matthias
    By-example aperiodic tilings are popular texture synthesis techniques that allow a fast, on-the-fly generation of unbounded and non-periodic textures with an appearance matching an arbitrary input sample called the ''exemplar''. But by relying on uniform random sampling, these algorithms fail to preserve the autocovariance function, resulting in correlations that do not match the ones in the exemplar. The output can then be perceived as excessively random. In this work, we present a new method which can well preserve the autocovariance function of the exemplar. It consists in fetching contents with an importance sampler taking the explicit autocovariance function as the probability density function (pdf) of the sampler. Our method can be controlled for increasing or decreasing the randomness aspect of the texture. Besides significantly improving synthesis quality for classes of textures characterized by pronounced autocovariance functions, we moreover propose a real-time tiling and blending scheme that permits the generation of high-quality textures faster than former algorithms with minimal downsides by reducing the number of texture fetches.