kaiming he 暗通道去雾和导向滤波

最新推荐文章于 2025-07-03 18:09:01 发布

代码喵酱

最新推荐文章于 2025-07-03 18:09:01 发布

阅读量8.4k

点赞数 1

CC 4.0 BY-SA版权

分类专栏：算法文章标签：去雾

本文链接：https://blog.youkuaiyun.com/maryhuan/article/details/64122609

算法专栏收录该内容

5 篇文章

订阅专栏

本文介绍了何凯明博士提出的导向滤波技术，并提供了该技术在MATLAB和OpenCV中的使用方法。导向滤波是一种用于边缘保护平滑的有效手段，可以在保持图像边缘细节的同时去除噪声。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

何凯明博士目前已经加入Facebook AI Reserach 。

他的blog地址：http://kaiminghe.com/

暗通道论文下载地址：http://kaiminghe.com/publications/cvpr09.pdf

导向滤波论文下载地址：http://kaiminghe.com/publications/eccv10guidedfilter.pdf

目前导向滤波已经加入MATLAB2014和Opencv3.0中：

===============MATLAB===============

imguidedfilter

Guided filtering of images

collapse all in page

Syntax

B = imguidedfilter(A,G)

B = imguidedfilter(A)

B = imguidedfilter(__,Name,Value,...)

Description

B = imguidedfilter(A,G) filters binary, grayscale, or RGB image A using the guided filter, where the filtering process is guided by imageG.G can be a binary, grayscale or RGB image and must have the same number of rows and columns asA.

example

B = imguidedfilter(A) filters input image A under self-guidance, using A itself as the guidance image. This can be used for edge-preserving smoothing of imageA.

B = imguidedfilter(__,Name,Value,...) filters the image A using name-value pairs to control aspects of guided filtering. Parameter names can be abbreviated.

Examples

Perform Edge-Preserving Smoothing Using Guided Filtering

This example shows how to perform edge-preserving smoothing using a guide filter.

Read an image into the workspace.

A = imread('pout.tif');

Smooth the image using imguidefilter. In this syntax, imguidedfilter uses the image itself as the guidance image.

Ismooth = imguidedfilter(A);

Display the original image and the smoothed image side-by-side.

imshowpair(A,Ismooth,'montage');

===============opencv3.0================

§ guidedFilter()

void cv::ximgproc::guidedFilter	(	InputArray	guide,
		InputArray	src,
		OutputArray	dst,
		int	radius,
		double	eps,
		int	dDepth = `-1`
	)

Simple one-line Guided Filter call.

If you have multiple images to filter with the same guided image then use GuidedFilter interface to avoid extra computations on initialization stage.

Parameters

guide	guided image (or array of images) with up to 3 channels, if it have more then 3 channels then only first 3 channels will be used.
src	filtering image with any numbers of channels.
dst	output image.
radius	radius of Guided Filter.
eps	regularization term of Guided Filter. eps 2 is similar to the sigma in the color space into bilateralFilter.
dDepth	optional depth of the output image.