Maximum Entropy Methods for Texture Synthesis: Theory and Practice
DOI10.1137/19M1307731zbMath1467.94014arXiv1912.01691OpenAlexW3125043764MaRDI QIDQ4999346
Agnès Desolneux, Bruno Galerne, Alain Durmus, Arthur Leclaire, Valentin De Bortoli
Publication date: 6 July 2021
Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1912.01691
Markov chainsmaximum entropyinformation geometrytexture synthesisLangevin algorithmconvolutional neural network
Computational methods in Markov chains (60J22) Artificial neural networks and deep learning (68T07) Monte Carlo methods (65C05) Discrete-time Markov processes on general state spaces (60J05) Computing methodologies for image processing (68U10) Applications of statistics (62P99) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Numerical analysis or methods applied to Markov chains (65C40) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Stochastic approximation (62L20) Measures of information, entropy (94A17) Statistical aspects of information-theoretic topics (62B10) Sampling theory in information and communication theory (94A20)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- A conditional multiscale locally Gaussian texture synthesis algorithm
- Reflection couplings and contraction rates for diffusions
- Texture synthesis and nonparametric resampling of random fields
- Reflection coupling and Wasserstein contractivity without convexity
- Sanov property, generalized I-projection and a conditional limit theorem
- Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds
- I-divergence geometry of probability distributions and minimization problems
- Problems and theorems in analysis. I. Series, integral calculus, theory of functions. Transl. from the German by Dorothee Aeppli
- Exponential convergence of Langevin distributions and their discrete approximations
- Introductory lectures on convex optimization. A basic course.
- Fast Langevin based algorithm for MCMC in high dimensions
- A survey of exemplar-based texture synthesis
- Equivalence of Julesz ensembles and FRAME models
- A parametric texture model based on joint statistics of complex wavelet coefficients
- Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
- Multiscale sparse microcanonical models
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
- The geometric foundations of Hamiltonian Monte Carlo
- Quantitative contraction rates for Markov chains on general state spaces
- Nonasymptotic bounds for sampling algorithms without log-concavity
- Exponential convergence in Lp-Wasserstein distance for diffusion processes without uniformly dissipative drift
- Information Theory and Statistical Mechanics
- On the Existence and Characterization of the Maxent Distribution Under General Moment Inequality Constraints
- Markov Chains
- Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods
- Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach. Part II: Theoretical Analysis
- A Texture Synthesis Model Based on Semi-Discrete Optimal Transport in Patch Space
- Random Phase Textures: Theory and Synthesis
- Monte Carlo sampling methods using Markov chains and their applications
- Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
- A Stochastic Approximation Method
This page was built for publication: Maximum Entropy Methods for Texture Synthesis: Theory and Practice
