A Mixture Autoregressive Image Generative Model on Quadtree Regions for Gaussian Noise Removal via Variational Bayes and Gradient Methods

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Saito, Shota, Nakahara, Yuta, Horinouchi, Kohei, Ichijo, Naoki, Kobayashi, Manabu, Matsushima, Toshiyasu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914557196238848
author Saito, Shota
Nakahara, Yuta
Horinouchi, Kohei
Ichijo, Naoki
Kobayashi, Manabu
Matsushima, Toshiyasu
author_facet Saito, Shota
Nakahara, Yuta
Horinouchi, Kohei
Ichijo, Naoki
Kobayashi, Manabu
Matsushima, Toshiyasu
contents This paper addresses the problem of image denoising for grayscale images. We propose a probabilistic image generative model that combines a quadtree region-partitioning model with a mixture autoregressive model, and propose a framework that reduces MAP (maximum a posteriori)-estimation-based denoising to the maximization of a variational lower bound. To maximize this lower bound, we develop an algorithm that alternately applies variational Bayes and gradient methods. We particularly demonstrate that the gradient-based update rule can be computed analytically without numerical computation or approximation. We carried out some experiments to verify that the proposed algorithm actually removes image noise and to identify directions for future improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11585
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Mixture Autoregressive Image Generative Model on Quadtree Regions for Gaussian Noise Removal via Variational Bayes and Gradient Methods
Saito, Shota
Nakahara, Yuta
Horinouchi, Kohei
Ichijo, Naoki
Kobayashi, Manabu
Matsushima, Toshiyasu
Computer Vision and Pattern Recognition
Machine Learning
This paper addresses the problem of image denoising for grayscale images. We propose a probabilistic image generative model that combines a quadtree region-partitioning model with a mixture autoregressive model, and propose a framework that reduces MAP (maximum a posteriori)-estimation-based denoising to the maximization of a variational lower bound. To maximize this lower bound, we develop an algorithm that alternately applies variational Bayes and gradient methods. We particularly demonstrate that the gradient-based update rule can be computed analytically without numerical computation or approximation. We carried out some experiments to verify that the proposed algorithm actually removes image noise and to identify directions for future improvement.
title A Mixture Autoregressive Image Generative Model on Quadtree Regions for Gaussian Noise Removal via Variational Bayes and Gradient Methods
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2605.11585