TEXTURE SYNTHESIS PEI YEAN LEE What is texture

TEXTURE SYNTHESIS PEI YEAN LEE

What is texture? • Images containing repeating patterns • Local & stationary

What is texture synthesis? • An alternative way to create textures • Construction of large regions of texture from small example images. Texture Synthesis Input Result

Goal of texture synthesis ? • Given: a texture sample • Find : synthesize a new texture that, when perceived by a human observer, appears to be generated by the same underlying process.

Application 1: Computer Graphics • Make things `look’ real – Rendering life-like animations

Application 2: Image Processing • Image compression • Image restoration and editing

Application 3: Computer Vision • To verify texture models for various tasks such as texture segmentation, recognition and Classification.

Some definitions • Image pyramid – A collection of images of reduced resolutions of the original 1: 1 image – 1: 2 n • Gaussian pyramid – Consists of a set of low-pass filtered versions of the image – Pg. 161 (Fig 7. 17)

Some definitions • Laplacian pyramid – Consists of a set of band-pass filtered versions of the image – Pg. 198 (Fig. 9. 8)

Approach 1: Physical simulation • Advantages: – produce texture directly on 3 D meshes, thus avoid texture mapping distortion problem • Disadvantages: – Applicable only to small texture class

Approach 2: Probability sampling • Zhu, Wu & Mumford (1998) – Markov Random Field (MRF) – Gibbs Sampling – Advantages: • Good approx. for wide range of textures – Disadvantages: • Computationally expensive

Approach 3: Feature matching • Model textures as a set of features and generate new images by matching the features in an example feature. • Advantages: – More efficient than MRF

Approach 3: Feature matching • Heeger & Bergen (1995) – model textures by matching marginal histograms of image pyramid – Advantages: • Works well for highly stochastic textures – Disadvantages: • Fails on more structured textures patterns such as bricks.

Approach 3: Feature matching • De Bonet (1997) – Synthesizes new images by randomizing an input texture sample while preserving cross-scale dependencies – Advantages: • Works better on structured textures – Disadvantages: • Can produce boundary artifacts if the input texture is not tileable.

Approach 3: Feature matching • Simoncelli & Portilla (1998) – Generate textures by matching the joint statistics of the image pyramids – Advantages: • Can capture global textural structures – Disadvantages: • Fails to preserve local patterns

Web demo • http: //graphics. stanford. edu/project s/texture/