Texture synthesis and nonparametric resampling of random fields
From MaRDI portal
Abstract: This paper introduces a nonparametric algorithm for bootstrapping a stationary random field and proves certain consistency properties of the algorithm for the case of mixing random fields. The motivation for this paper comes from relating a heuristic texture synthesis algorithm popular in computer vision to general nonparametric bootstrapping of stationary random fields. We give a formal resampling scheme for the heuristic texture algorithm and prove that it produces a consistent estimate of the joint distribution of pixels in a window of certain size under mixing and regularity conditions on the random field. The joint distribution of pixels is the quantity of interest here because theories of human perception of texture suggest that two textures with the same joint distribution of pixel values in a suitably chosen window will appear similar to a human. Thus we provide theoretical justification for an algorithm that has already been very successful in practice, and suggest an explanation for its perceptually good results.
Recommendations
Cites work
- scientific article; zbMATH DE number 3513115 (Why is no real title available?)
- scientific article; zbMATH DE number 854585 (Why is no real title available?)
- A parametric texture model based on joint statistics of complex wavelet coefficients
- Bootstrap in Markov-sequences based on estimates of transition density
- Classification of binary random patterns
- Equivalence of Julesz ensembles and FRAME models
- Image analysis with partially ordered Markov models.
- Mixing: Properties and examples
- Nonparametric resampling for homogeneous strong mixing random fields
- The jackknife and the bootstrap for general stationary observations
- The local bootstrap for Markov processes
Cited in
(21)- A Fast Nonparametric Noncausal MRF-Based Texture Synthesis Scheme Using a Novel FKDE Algorithm
- On a nonparametric resampling scheme for Markov random fields
- Symmetric noncausal spatial models for 2-D signals with applications in stochastic texture modeling
- Nonparametric link prediction in large scale dynamic networks
- Wasserstein loss for image synthesis and restoration
- Regularized non-local total variation and application in image restoration
- TILT: transform invariant low-rank textures
- Consistency of a nonparametric conditional quantile estimator for random fields
- Frequency polygons for continuous random fields
- A variational framework for exemplar-based image inpainting
- Redundancy in Gaussian random fields
- An exploratory analysis approach for understanding variation in stochastic textured surfaces
- Vertically weighted averages in Hilbert spaces and applications to imaging: fixed-sample asymptotics and efficient sequential two-stage estimation
- Kernel regression estimation for continuous spatial processes
- A texture synthesis model based on semi-discrete optimal transport in patch space
- scientific article; zbMATH DE number 64022 (Why is no real title available?)
- On bootstrapping panel factor series
- A Monitoring and Diagnostic Approach for Stochastic Textured Surfaces
- Maximum entropy methods for texture synthesis: theory and practice
- A conditional multiscale locally Gaussian texture synthesis algorithm
- scientific article; zbMATH DE number 4054780 (Why is no real title available?)
This page was built for publication: Texture synthesis and nonparametric resampling of random fields
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q449946)
