专栏首页机器学习、深度学习图像拼接--A multiresolution spline with application to image mosaics

图像拼接--A multiresolution spline with application to image mosaics

A multiresolution spline with application to image mosaics 《Acm Trans on Graphics》 , 1983 , 2 (4) :217-236

本文主要介绍使用 Multiresolution Spline算法来消除图像拼接之间的痕迹 A technical problem common to all applications of photomosaics is joining two images so that the edge between them is not visible 如下图所示:两个图像拼接线中间有一个明显痕迹

首先介绍了一下要解决的问题

这里使用 image spline 来表示消除痕迹的手段 We will use the term image spline to refer to digital techniques for making these adjustments.

这里我们先描述一个简化版本的问题,一维信号拼接 这里我们介绍 a weighted average splining technique.

在拼接的邻域乘以一个权重系数,然后叠加两个图像(sum),这个算法的关键是 T 宽度的选择,宽度太小 消除痕迹不明显,仍有痕迹残留,宽度太大,会将边界附近的边缘特征削弱 If T is small compared to image features, then the boundary may still appear as a step in image gray level, albeit a somewhat blurred step. 宽度过大会造成一个物体重影,类似双曝光现象 If, on the other hand, T is large compared to image features, features from both images may appear superimposed within the transition zone, as in a photographic double exposure.

Clearly, the size of the transition zone, relative to the size of image features, plays a critical role in image splining 所以这个宽度的选择和图像特征尺寸大小密切相关。

To eliminate a visible edge the transition width should be at least comparable in size to the largest prominent features in the image. On the other hand, to avoid a double exposure effect, the zone should not be much larger than the smallest prominent image features. There is no choice of T which satisfies both requirements in the star images of Figure 3 because these contain both a diffuse background and small bright stars.

上面的两难问题我们可以换一种方式表达:image spatial frequency content. In particular, a suitable T can only be selected if the images to be splined occupy a relatively narrow spatial frequency band.

如果图像只分高频信息和低频信息,那么在高频信息中我们使用较小的 T,在低频信息中选择较大 T

The approach proposed here is that such images should first be decomposed into a set of band-pass component images. A separate spline with an appropriately selected T can then be performed in each band. Finally, the splined band-pass components are recombined into the desired mosaic image. We call this approach the multiresolution spline. 这里我们将图像分解为多个 band-pass component images,在每个 band 中进行拼接,最后叠加所有 components

以上就是 multiresolution spline 大致思路。

下面是算法实现的具体细节 2. Basic Pyramid Operations A sequence of low-pass filtered images Go, G1 … , GN can be obtained by repeatedly convolving a small weighting function with an image

Convolution with a Gaussian has the effect of low-pass filtering the image. Pyramid construction is equivalent to convolving the image with a set of Gaussian-like functions to produce a corresponding set of filtered images. Because of the importance of the multiple filter interpretation, we shall refer to this sequence of images Go,G1 … GN as the Gaussian pyramid.

The Gaussian pyramid is a set of low-pass filtered images. In order to obtain the band-pass images required for the multiresolution spline we subtract each level of the pyramid from the next lowest level.

This difference of Gaussian-like functions resembles the Laplacian operators commonly used in the image processing [5], so we refer to the sequence Lo, L1 … , LN as the Laplacian pyramid.

multiresolution spline algorithm:

The idea behind multi-band blending is to blend low frequencies over a large spatial range, and high frequencies over a short range.

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

我来说两句

0 条评论
登录 后参与评论

相关文章

  • 语义分割--Loss Max-Pooling for Semantic Image Segmentation

    Loss Max-Pooling for Semantic Image Segmentation CVPR2017 https://arxiv.org/...

    用户1148525
  • 人群密度估计--CrowdNet: A Deep Convolutional Network for Dense Crowd Counting

    CrowdNet: A Deep Convolutional Network for Dense Crowd Counting published in ...

    用户1148525
  • 图像拼接--Creating full view panoramic image mosaics and environment maps

    版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/zhangjunhit/article/de...

    用户1148525
  • 用超图进行超真实感图像填充(CS CV)

    图像修复是计算机视觉中的一项重要任务,它可能依赖于图像的全局信息来填充缺失的数据。现有的方法大多使用注意力机制来学习图像的全局上下文。由于无法捕捉全局上下文,这...

    凌茜
  • lazynlp:构建大规模语料库的"懒人"工具箱

    推荐Github上一个新鲜出炉的NLP工具:lazynlp,作者是 Chip Huyen ,曾经在斯坦福讲受过一门课程:TensorFlow for Deep ...

    AINLP
  • 用于真实图像编辑的域内GAN反转(CS.CV)

    最近的工作表明,当训练合成图像时,在生成对抗网络(GAN)的潜在空间中会出现各种可控制的语义。但是,很难将这些学习到的语义用于真实图像编辑。将真实图像馈送到训练...

    蔡小雪7100294
  • idea中下载并配置稳定版本的MAVEN,电脑环境配置 + setting.xml文件配置

  • Maven安装配置详细教程

    你还在为导入jar包而苦恼吗?常常找不到jar包,不知道从哪导入,就算导入了可能还会依赖冲突,目录杂乱,那么maven你值得拥有。 什么是jar包?jar [...

    唔仄lo咚锵
  • 【论文推荐】最新八篇图像检索相关论文—三元组、深度特征图、判别式、卷积特征聚合、视觉-关系知识图谱、大规模图像检索

    WZEARW
  • 【论文推荐】最新6篇图像描述生成相关论文—语言为枢纽、细粒度、生成器、注意力机制、策略梯度优化、判别性目标

    【导读】专知内容组整理了最近六篇图像描述生成(Image Caption)相关文章,为大家进行介绍,欢迎查看! 1. Unpaired Image Captio...

    WZEARW

扫码关注云+社区

领取腾讯云代金券