While precise spectral control can be achieved through sparse convolution, corresponding state of the art noise models are typically too expensive for solid noise. We introduce an alternative, wave-based procedural noise model, fast enough to be used in any dimension. We express the noise in the spectral domain and then apply an inverse Fourier transform (FT), requiring the computation of a multidimensional integral. Our contribution is a novel, efficient way to perform this computation, using a sum of precomputed complex-valued hyperplanar wave-functions, oriented in random directions. We show that using suitable wave profiles and combination operators, our model is able to extend to 3D a number of Gaussian and non-Gaussian noises, including Gabor, by-example and Phasor noises, as well as generate novel cellular noises. Our versatile and controllable solid noise model is very compact, a key feature for complex power spectrum and animated noises. We illustrate this through the design of 2D, 3D, and 3D+t materials using color, transparency and style transfer functions.

We present a method for retiming existing 3D animations able to handle seamlessly arbitrary impulse-like user gestures, thus enabling expressive video-based control inspired from common review sessions used in animation studios. The approach works in recording two videos with fast, impulse-based, gestures: one synchronized with the existing 3D animation and another featuring a new time sequence. We then propose an automatic generation of a modified 3D animation retimed to match the sequences of the second video. To this end, we introduce a robust and automatic method relying on Dynamic Time Warping able to compute the sequential correspondence between the timings of the impulse gestures. The method can adapt to various individual gestures without requiring dedicated learning, and can take into account the semantic integrity of the original 3D animation after retiming.

Abstract We introduce a novel semi‐procedural approach that avoids drawbacks of procedural textures and leverages advantages of data‐driven texture synthesis. We split synthesis in two parts: 1) structure synthesis, based on a procedural parametric model and 2) color details synthesis, being data‐driven. The procedural model consists of a generic Point Process Texture Basis Function (PPTBF), which extends sparse convolution noises by defining rich convolution kernels. They consist of a window function multiplied with a correlated statistical mixture of Gabor functions, both designed to encapsulate a large span of common spatial stochastic structures, including cells, cracks, grains, scratches, spots, stains, and waves. Parameters can be prescribed automatically by supplying binary structure exemplars. As for noise‐based Gaussian textures, the PPTBF is used as stand‐alone function, avoiding classification tasks that occur when handling multiple procedural assets. Because the PPTBF is based on a single set of parameters it allows for continuous transitions between different visual structures and an easy control over its visual characteristics. Color is consistently synthesized from the exemplar using a multiscale parallel texture synthesis by numbers, constrained by the PPTBF. The generated textures are parametric, infinite and avoid repetition. The data‐driven part is automatic and guarantees strong visual resemblance with inputs.