2011
DOI: 10.1109/mcg.2010.105
|View full text |Cite
|
Sign up to set email alerts
|

Building and Using a Database of One Trillion Natural-Image Patches

Abstract: Many example-based image processing algorithms operate on image patches (texture synthesis, resolution enhancement, image denoising, and so on). However, inaccessibility to a large, varied collection of image patches has hindered widespread adoption of these methods. The authors describe the construction of a database of one trillion image patches and demonstrate its research utility.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2012
2012
2018
2018

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 10 publications
(5 citation statements)
references
References 7 publications
0
5
0
Order By: Relevance
“…However, while most image priors (parametric, non-parametric, learning-based) [2,14,20,16,23] as well as studies on image statistics [13,7] are restricted to local image patches or kernels, little is known about their dependence on patch size. Hence another question of practical importance is the following: What is the potential restoration gain from an increase in patch size?…”
Section: Introductionmentioning
confidence: 99%
“…However, while most image priors (parametric, non-parametric, learning-based) [2,14,20,16,23] as well as studies on image statistics [13,7] are restricted to local image patches or kernels, little is known about their dependence on patch size. Hence another question of practical importance is the following: What is the potential restoration gain from an increase in patch size?…”
Section: Introductionmentioning
confidence: 99%
“…Second, predictive power quantifies how effective patch matches from a database are at constraining the solution toward the ground truth. Expressiveness is similar to the "reconstruction error" examined in [2] for image databases with trillions of patches.…”
Section: Understanding the Quality Of Scene Matchesmentioning
confidence: 79%
“…In fact, images shown in Figure 1 have been obtained as the Kronecker product of the original image and the vector [1, 0.6, 0.4] (see [8] for more facts concerning the Kronecker product, tensors, and operations on them). On the other hand, one can already meet databases containing one trillion images (see [9]) and one can expect thatdue to cloud resourceseven larger databases can be virtually organized. Recent examples which indicate that there are needs for cloud image databases and for image classification, grouping, clustering etc.…”
Section: Motivationmentioning
confidence: 99%