Bi-Layer textures: a Model for Synthesis and Deformation of Composite Textures

Analysis synthesis + deformations structure layer 1 layer (standard) 2 layers (our model) synthesis + deformations noise 1 noise 2 mask 1 mask 2 spatially-varying noise layer Figure 1: Our noise model decomposes an input exemplar as a structure layer and a noise layer. The noise layer captures a spatially varying Gaussian noise as a blend of stationary noises. Large outputs are synthesized on-the-fly by synchronized synthesis of the layers. Variety can be achieved at the synthesis stage by deforming the structure layer while preserving fine scale appearance, encoded in the noise layer. Abstract We propose a bi-layer representation for textures which is suitable for on-the-fly synthesis of unbounded textures from an input exemplar. The goal is to improve the variety of outputs while preserving plausible small-scale details. The insight is that many natural textures can be decomposed into a series of fine scale Gaussian patterns which have to be faithfully reproduced, and some non-homogeneous, larger scale structure which can be deformed to add variety. Our key contribution is a novel, bi-layer representation for such textures. It includes a model for spatially-varying Gaussian noise, together with a mechanism enabling synchronization with a structure layer. We propose an automatic method to instantiate our bi-layer model from an input exemplar. At the synthesis stage, the two layers are generated independently, synchronized and added, preserving the consistency of details even when the structure layer has been deformed to increase variety. We show on a variety of complex, real textures, that our method reduces repetition artifacts while preserving a coherent appearance.