Procedural texture synthesis by locally controlled spot noise

Procedural noises based on power spectrum definition and random phases have been widely used for procedural texturing, but using a noise process with random phases limits the types of possible patterns to Gaussian patterns (i.e. irregular textures with no structural features). Local Random Phase (LRP) Noise has introduced control over structural features in a noise model by fixing the frequencies and phase information of desired features, but this approach requires storing these frequencies. Space distortion and randomization must also be used to avoid repetitions and periodicity. In this paper, we present a noise model based on non-uniform random distributions of multiple Gaussian functions for synthesizing semi-structured textures. We extend the LRP noise model by using a spot noise based on a controlled distribution of kernels (spots), as an alternative formulation to local noises aligned on a regular grid. Spots are created as a combination of Gaussian functions to match either a specific power spectrum or a user-defined texture element. Our noise model improves the control over local structural features while keeping the benefits of LRP noise.

[1]  Klaus Mueller,et al.  A frequency-sensitive point hierarchy for images and volumes , 2003, IEEE Visualization, 2003. VIS 2003..

[2]  Ares Lagae,et al.  Procedural noise using sparse Gabor convolution , 2009, SIGGRAPH '09.

[3]  Jean-Michel Dischler,et al.  Multiple kernels noise for improved procedural texturing , 2012, The Visual Computer.

[4]  J. P. Lewis,et al.  Algorithms for solid noise synthesis , 1989, SIGGRAPH.

[5]  Alexei A. Efros,et al.  Image quilting for texture synthesis and transfer , 2001, SIGGRAPH.

[6]  Georgy L. Gimel'farb,et al.  Texture modelling with nested high-order Markov-Gibbs random fields , 2015, Comput. Vis. Image Underst..

[7]  Ken Perlin,et al.  An image synthesizer , 1988 .

[8]  David S. Ebert,et al.  Enhancing the Interactive Visualization of Procedurally Encoded Multifield Data with Ellipsoidal Basis Functions , 2006, Comput. Graph. Forum.

[9]  J. van Wijk,et al.  Spot noise texture synthesis for data visualization , 1991, SIGGRAPH.

[10]  Anton Alstes.  Wang Tiles for Image and Texture Generation , 2004 .

[11]  Ulrich Amsel.  Texturing And Modeling A Procedural Approach , 2016 .

[12]  Bruno Galerne,et al.  Gabor noise by example , 2012, ACM Trans. Graph..

[13]  A.V. Oppenheim,et al.  The importance of phase in signals , 1980, Proceedings of the IEEE.

[14]  Ares Lagae,et al.  Procedural isotropic stochastic textures by example , 2010, Comput. Graph..

[15]  Andrew W. Fitzgibbon,et al.  A Buyer's Guide to Conic Fitting , 1995, BMVC.

[16]  Jean-Michel Dischler,et al.  Local random-phase noise for procedural texturing , 2014, ACM Trans. Graph..

[17]  Jean-Michel Dischler,et al.  Procedural texture particles , 2010, I3D '10.

[18]  Jean-Michel Dischler,et al.  Multi‐scale Assemblage for Procedural Texturing , 2012, Comput. Graph. Forum.

[19]  Robert van Liere,et al.  Divide and Conquer Spot Noise , 1997 .

[20]  Gerald M. Flachs,et al.  Markov random field texture models for classification , 1990, Defense, Security, and Sensing.

[21]  Ares Lagae,et al.  A procedural object distribution function , 2005, TOGS.

[22]  Ares Lagae,et al.  A Survey of Procedural Noise Functions , 2010, Comput. Graph. Forum.

[23]  Jean-Michel Dischler,et al.  On-the-fly multi-scale infinite texturing from example , 2013, ACM Trans. Graph..