Sketch2Photo: Internet Image Montage
- Tao Chen | no link available
- Ming-Ming Chen | cg.cs.tsinghua.edu.cn:8080/cmm
- Ping Tan | www.ece.nus.edu.sg/stfpage/eletp
- Ariel Shamir | www.faculty.idc.ac.il/arik/site/index.asp
- Shi-Min Hu | cg.cs.tsinghua.edu.cn/prof_hu.htm
- Tsinghua University | www.tsinghua.edu.cn/qhdwzy/index.jsp
- National University of Singapore | www.nus.edu.sg
- The Interdisciplinary Center | portal.idc.ac.il/he
- Tsinghua University | www.tsinghua.edu.cn/qhdwzy/index.jsp
Abstract
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.
Press
The Telegraph
telegraph.co.uk/technology/news/6265876/PhotoSketch-picture-software-wins-plaudits.html | Archive (pdf)
Der Spiegel
spiegel.de/netzwelt/gadgets/0,1518,653734,00.html | Archive (pdf) | Translated (pdf)
Net Explorateur
netexplorateur.org/?q=en/top-10 ("10 most promising digital initiatives in 2010") (defunct)
telegraph.co.uk/technology/news/6265876/PhotoSketch-picture-software-wins-plaudits.html | Archive (pdf)
Der Spiegel
spiegel.de/netzwelt/gadgets/0,1518,653734,00.html | Archive (pdf) | Translated (pdf)
Net Explorateur
netexplorateur.org/?q=en/top-10 ("10 most promising digital initiatives in 2010") (defunct)
Downloads
|
|
|
|
|
|
System Pipeline
Online Video
User information posted to YouTube:
Pertinent comments from YouTube page:
Results
This information was found here:
www.cs.sfu.ca/~pingtan/Projects/Sketch2Photo/index.htm
www.cs.sfu.ca/~pingtan/Projects/Sketch2Photo/index.htm
See Also: