Image Completion Using Dynamic-Scale Patch Matching and Layer-Wise Chain Optimization

XU Gang; MA Shuang

doi:10.3969/j.issn.0372-2112.2015.03.018

您当前的位置：

首页 >

文章列表页 >

Image Completion Using Dynamic-Scale Patch Matching and Layer-Wise Chain Optimization

更新时间：2025-07-16

- Image Completion Using Dynamic-Scale Patch Matching and Layer-Wise Chain Optimization
- Acta Electronica Sinica Vol. 43, Issue 3, Pages: 529-535(2015)
- 作者机构：
  
  华北电力大学电气与电子工程学院,北京,102206
- 作者简介：
- 基金信息：
  
  Fundamental Research Funds for the Central Universities (No.13XS01)
- DOI：10.3969/j.issn.0372-2112.2015.03.018
  CLC： TP391
- Published：2015
- 稿件说明：
移动端阅览
XU Gang, MA Shuang. Image Completion Using Dynamic-Scale Patch Matching and Layer-Wise Chain Optimization[J]. Acta Electronica Sinica, 2015, 43(3): 529-535.
DOI：

XU Gang, MA Shuang. Image Completion Using Dynamic-Scale Patch Matching and Layer-Wise Chain Optimization[J]. Acta Electronica Sinica, 2015, 43(3): 529-535. DOI： 10.3969/j.issn.0372-2112.2015.03.018.

摘要

针对由块间像素值突变引起的修复质量下降问题

提出一种基于动态尺度块匹配的链式优化图像修复算法.该方法依据先验信息与结构特征确定当前修复层所有图像块的候选匹配块数量;构建多尺度块匹配搜索模型

以二次搜索定位目标候选块

形成图像修复可行解空间.在候选块集合约束下

建立基于块间关联匹配特性的链式优化修复模型

并采用动态规划法求解当前修复层的最优匹配块集合

实现对图像的由外向内修复.实验结果表明

算法对多种自然图像的修复达到了令人满意的效果.

Abstract

In order to reduce visually inconsistent results caused by sudden change of pixel values between patches

a novel image completion method based on dynamic-scale patch matching and layer-wise optimization was proposed.During patch searching

the number of candidate patches for the current layer was calculated through the analysis of prior knowledge and structure features;meanwhile

a multi-scale patch searching model was given to obtain the best candidate patches.Those patches constituted the feasible solution space for image completion.With the intrinsic characteristics and relevance of adjacent patches taken into consideration

image completion was abstracted as a chain optimization problem.The layer-wise chain optimization model was established and solved through dynamic programming.The optimal patches for the current layer were obtained and the image was repaired from the outside to the inside layer by layer.Experimental results demonstrate both the effectiveness and efficiency of the proposed algorithm for various natural images.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Optimization of Perspective Distortion for Image Completion Based on the Large Displacement View

Related Author

LIU Chun-xiao

PENG Qun-sheng

YANG Ying-zhen

WANG Jin

CHEN Wei

Related Institution

State Key Laboratory of CAD&CG, Zhejiang University

⁰