增强与改善图像的神奇算法（5）草图合成照片 / 后期非编 - 中文汉化|专业汉化网站

离线 jiwendu2002

楼主发表于： 2012-01-01 只看楼主倒序阅读

举报

0F

l 增强与改善图像的神奇算法（5）草图合成照片

Sketch2Photo: Internet Image Montage 草图合成照片：网络图像合成

Tao Chen¹ Ming-Ming Cheng¹ Ping Tan² Ariel Shamir³ Shi-Min Hu¹

¹TNList, Department of Computer Science and Technology, Tsinghua University
²National University of Singapore ³The Interdisciplinary Center

清华大学计算机科学与技术学院，新加坡国立大学，跨学科研究中心

Abstract摘要

We present a system that composes a realistic picture from a simple freehand sketch annotated with text labels. The composed picture is generated by seamlessly stitching several photographs in agreement with the sketch and text labels; these are found by searching the Internet. Although online image search generates many inappropriate results, our system is able to automatically select suitable photographs to generate a high quality composition, using a filtering scheme to exclude undesirable images. We also provide a novel image blending algorithm to allow seamless image composition. Each blending result is given a numeric score, allowing us to find an optimal combination of discovered images. Experimental results show the method is very successful; we also evaluate our system using the results from two user studies.

我们介绍的系统可以从一个简单的，带有文本标示的手绘草图构成一幅逼真的图像。这个图像是由可以通过网络检索获得，与草图和文本标示相符的图片精确地融合在一起。尽管联机图像检索会带来许多不确定结果，我们的系统仍然能够通过过滤方案排除不要的图像，自动筛选合适的图片产生高质量的融合效果。我们也提供了一个新颖的图像混合算法，去达到精确的图像融合。每一个融合效果都会给出一个数值得分，使我们在遇到的图像中找到最佳的融合。实验结果表明，算法非常有效；用户调查结果显示了同样的判断。

Paper论文

Sketch2Photo: Internet Image Montage 草图转照片：互联网图像合成
ACM SIGGRAPH ASIA 2009, ACM Transactions on Graphics, to appear美国计算机学会，计算机绘图专业，亚洲2009，美国计算机学会图形学汇刊
作者：Tao Chen, Ming-Ming Cheng, Ping Tan, Ariel Shamir, Shi-Min Hu

System Pipeline 系统流程

1. 绘制出简略的草图，并输入场景项的名称--关键词，如背景—tree，场景项：人物投掷—man throw，跳跃的小狗—dog jump，抛出的飞碟—frisbee。

2. 检索到的背景图片、场景项挑选

3. 图像合成的几个优化方案选择

4. 合成照片排名输出

检索结果举例

图3.背景和场景项筛选

a．筛选背景，从上到下每行显示：按照关键词“tree”检索图像，与“tree”有关的图像筛选完毕，排列供选择；b---d，场景项筛选，从上到下每行显示：按照关键词“人物投掷”、“狗跳跃”、“飞碟”显示出检索的图像。

Composition Results 合成效果

用户绘制的草图最终输出效果图加入场景项资源选择

Video or Supplementary Materials

视频或补充资料

1. Intermediate results中间结果

General supplementary materials, including intermediate results and comparisons. [pdf]

整个补充资料，包括中间结果和对照。

2. User studies用户研究

High resolution compositions and detailed statistics of the user studies. [pdf]高分辨率合成品和用户调研的详细统计数字

3. Software 软件

The original Sketch2Photo downloaded and processed images from internet after user drawing sketches. Although it was a brilliant concept, we found this impracticable for users -- they lost patience while waiting for the hours of downloading and processing. Now, we bring the Sketch2Photo to a new phase: User can watch the result almost instantly after him drawing the sketch. We achieve this by a server-client scheme in which the server pre-processes all the images offline, then the client will only need to query desired images by sketching. We also modified the query algorithm so that it now takes almost no time (but you still have to wait for downloading those queried images). We also add more interactive functions to make the use more flexible.

用户绘制好草图后，从互联网下载草图转照片（Sketch2photo）软件和处理的图像。虽然这是一个卓越的想法，我们发现对用户却难以行得通…..，他们总是在等待下载和处理的时间中失去耐心。现在我们的sketch2photo达到一个新的阶段：用户可以在他绘制完草图后立即看到结果。我们使用服务器-客户机方案，由服务器在离线时对所有图像进行预处理，然后客户机仅需要提出草图要求的图像请求即可。同时请求的算法也进行了修改，这样几乎不用花费任何时间（除非你要等待那些想要的图像下载）。我们也添加了许多交互功能，更方便使用。

Note this software is still very primitive, we release it on our cooperative partner, M.I.S.Technology Co.’s website (download guide) for a public test. There are some unfinished functions and differences from the previous Sketch2Photo. We list them below:

注意这个软件仍然非常初级，在我们的合作伙伴中（M.I.S.Technology 公司网站下载指南)发布进行公开测试。有些没完善的功能和与早期sketch2photo不同的地方，列表如下：

1. It only supports limited keywords for backgrounds and scene items, which are pre-processed on our server. We will add more available keywords in further version, and add the function to let the server download new images according to user inputted keywords if they are not exist in the server.

仅支持有限的，在我们的服务器上预处理过的，背景和场景项目关键词。在后续的版本中将添加更多可以用到的关键词，并增加让服务器按照用户输入的关键词，下载服务器上尚不存在的新图像的功能。

2. The querying by sketch method is now very fast, but suffers the quality loss. We are stilling looking for the balance between quality and speed. There is also no horizontal line alignment, although the horizontal information contains in backgrounds. It will be added back in next version.

依据草图方式查询现在非常快，但也会带来质量损失。我们始终在速度和质量之间寻求平衡。虽然背景中包含有水平线信息，却没有水平线校准。这将在下一个版本中加回去。

3. Since in this version we allow user adjusting object size and position, the composition items combination cannot be optimized as before, this will be added together with horizontal alignment.

因为在这一个版本中，我们允许用户调整对象的对象和位置，混合项目排布不能像以前那样被优化。优化功能将与水平校准一起加入。

4. The advanced composition is absent. We are working on a more efficient implementation, and it’s not bug free for release. So the current composition result looks trivial.

缺少现代的构图。我们工作于一个更有效率的工具，它不是免费发布或开放源代码。所以流行的合成效果图看起来没有什么价值。

BugFree 有两层意思：一是希望软件中的缺陷越来越少直到没有，Free嘛；二是表示它是免费且开放源代码的，大家可以自由使用传播。

So if you hope to use this software to generate gorgeous photographs, you should probably skip this version, but we welcome you to test and give us feed back. We will continue improving it according to above four points, and any suggestions are welcome!

如果你需要使用这个软件去生成漂亮的照片，你应该略过这个版本，但我们欢迎你做测试并作出反馈。我们将从上述4个方面继续作出改进，任何的建议都受欢迎！

Sketch2photo练习试用：点击这里试用 (中文)

更新：基于网页的草图转照片应用程序点击这里试用 (中文) 合作方：腾讯公司

Acknowledgments

This work was supported by the National Basic Research Project of China (Project Number 2006CB303106), the National High Technology Research and Development Program of China (Project Number 2009AA01Z330) and FDCT, Macau (Project Number 008/2008/A1). Tan Ping is supported by Singapore FRC Grant R-263-000-477-112.

感谢：本工作得到国家重点基础研究项目支持(项目号 2006CB303106)，国家高技术研究发展计划（项目号2009AA01Z330）等多项科研项目资助。

Note

Original Name: PhotoSketch. We change the name since it's conflict with existing software: http://www.brainstormllc.com/.

本工作作为实验性项目，实际应用尚需作出许多改进，有关图像版权，原代码注册保护等方面等等。。。，但想法有趣，大家一睹为快。