ACM Home Page
Please provide us with feedback. Feedback
PatchMatch: a randomized correspondence algorithm for structural image editing
Full text PdfPdf (37.38 MB)
Source
ACM Transactions on Graphics (TOG) archive
Volume 28 ,  Issue 3  (August 2009) table of contents
Proceedings of ACM SIGGRAPH 2009
SESSION: Fast image processing and retargeting table of contents
Article No. 24  
Year of Publication: 2009
ISSN:0730-0301
Also published in ...
Authors
Connelly Barnes  Princeton University
Eli Shechtman  Adobe Systems and University of Washington
Adam Finkelstein  Princeton University
Dan B Goldman  Adobe Systems
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 98,   Downloads (12 Months): 273,   Citation Count: 0
Additional Information:

appendices and supplements   abstract   references   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1531326.1531330
What is a DOI?


ABSTRACT

This paper presents interactive image editing tools using a new randomized algorithm for quickly finding approximate nearest-neighbor matches between image patches. Previous research in graphics and vision has leveraged such nearest-neighbor searches to provide a variety of high-level digital image editing tools. However, the cost of computing a field of such matches for an entire image has eluded previous efforts to provide interactive performance. Our algorithm offers substantial performance improvements over the previous state of the art (20-100x), enabling its use in interactive editing tools. The key insights driving the algorithm are that some good patch matches can be found via random sampling, and that natural coherence in the imagery allows us to propagate such matches quickly to surrounding areas. We offer theoretical analysis of the convergence properties of the algorithm, as well as empirical and practical evidence for its high quality and performance. This one simple algorithm forms the basis for a variety of tools -- image retargeting, completion and reshuffling -- that can be used together in the context of a high-level image editing application. Finally, we propose additional intuitive constraints on the synthesis process that offer the user a level of control unavailable in previous methods.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

1
2
 
3
 
4
Cho, T. S., Butman, M., Avidan, S., and Freeman, W. 2008. The patch transform and its applications to image editing. CVPR.
 
5
Criminisi, A., Pérez, P., and Toyama, K. 2003. Object removal by exemplar-based inpainting. CVPR 2, 721.
6
7
 
8
9
10
 
11
 
12
13
 
14
Komodakis, N., and Tziritas, G. 2007. Image completion using efficient belief propagation via priority scheduling and dynamic pruning. IEEE Transactions on Image Processing 16, 11, 2649--2661.
15
 
16
17
18
19
20
21
 
22
Mount, D. M., and Arya, S., 1997. ANN: A library for approximate nearest neighbor searching, Oct. 28.
 
23
24
25
26
27
 
28
Simakov, D., Caspi, Y., Shechtman, E., and Irani, M. 2008. Summarizing visual data using bidirectional similarity. In CVPR.
29
 
30
31
32
 
33
34
 
35
 
36
Wolf, L., Guttmann, M., and Cohen-Or, D. 2007. Non-homogeneous content-driven video-retargeting. In ICCV.

Collaborative Colleagues:
Connelly Barnes: colleagues
Eli Shechtman: colleagues
Adam Finkelstein: colleagues
Dan B Goldman: colleagues